INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    71.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    terms related to political figures and structures in a political context

    New Auto-Interp
    Negative Logits
    andExpect
    -0.56
    styleType
    -0.52
    :✨
    -0.51
    GEBURTSDATUM
    -0.51
     Superhost
    -0.49
    estacks
    -0.48
     Audiodateien
    -0.48
    AsNil
    -0.47
     referenties
    -0.47
    zheimer
    -0.46
    POSITIVE LOGITS
    ActionCreators
    0.49
    Poli
    0.45
     Poli
    0.42
    political
    0.41
     politicians
    0.41
     political
    0.39
     Political
    0.38
     Polit
    0.37
    團體
    0.36
     politics
    0.36
    Act Density 0.000%

    No Known Activations