INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    31.375
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    patterns and structural elements in writing, particularly in programming or technical contexts

    New Auto-Interp
    Negative Logits
     pungkas
    -0.35
     miteinander
    -0.34
     öğ
    -0.32
     Förderung
    -0.31
    Hochspringen
    -0.31
     régler
    -0.30
    👄
    -0.30
    wnież
    -0.29
     cintura
    -0.29
     değişik
    -0.29
    POSITIVE LOGITS
    rrggbb
    0.60
    исленность
    0.59
     يتيمه
    0.59
    IntoConstraints
    0.56
    <tfoot>
    0.53
    bibfield
    0.53
     CLAIM
    0.52
     wiſſen
    0.52
     Claim
    0.51
     beſch
    0.50
    Act Density 0.928%

    No Known Activations