INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    33
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to medical or healthcare topics

    New Auto-Interp
    Negative Logits
     nawr
    -0.41
    Legături
    -0.39
     aşk
    -0.35
     Ausbau
    -0.34
     kullanım
    -0.33
     Durchführung
    -0.32
     réglage
    -0.32
     dirait
    -0.30
     juventud
    -0.29
     naudoti
    -0.28
    POSITIVE LOGITS
    <unused8>
    0.68
    <unused14>
    0.68
    <unused47>
    0.68
    <unused3>
    0.67
    <unused23>
    0.67
    <unused41>
    0.67
    <unused43>
    0.67
    <unused51>
    0.67
    <unused52>
    0.67
    <unused68>
    0.67
    Act Density 3.270%

    No Known Activations