Training NeuralProphet and excluding the target variable from model input

[FHohnstein]

I want to a model multivariate time series. However, I do not want the target variable to be part of the input of model. Lets make an example:

feature1 = np.sin(np.linspace(0, 2np.pi, 100))
feature2 = np.cos(np.linspace(0, 2np.pi, 100))
target = feature1 + feature2

I want to model the 'target' using 'feature1' and 'feature2', without the target being part of the model input. The model shall learn that 'target = feature1 + feature2', by looking at the past values of 'feature1' and 'feature2' not at the past values of 'target'.

Is there a way to to that ?