Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    35.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to configurations, systems, or components in programming or technology contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    __).
    -0.40
     bubuk
    -0.39
     Messung
    -0.36
    retudo
    -0.35
     kõik
    -0.35
    reszcie
    -0.35
     dapur
    -0.35
     vastaan
    -0.33
     quieran
    -0.33
     yoksa
    -0.33
    POSITIVE LOGITS
     propOrder
    0.69
    rrggbb
    0.66
    CppMethod
    0.56
    0.54
    setVerticalGroup
    0.54
     Administrativna
    0.54
    LayoutStyle
    0.53
    transQ
    0.53
    Gön
    0.52
    PostInfinity
    0.51
    Act Density 0.000%

    No Known Activations