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
    65
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    function definitions and class declarations in code

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    AddWithValue
    -0.42
     estekak
    -0.40
    คง
    -0.37
    zehnten
    -0.36
     utafitiHapana
    -0.35
     probably
    -0.34
    vestre
    -0.34
    ）-
    -0.34
     sensibly
    -0.34
     obviously
    -0.34
    POSITIVE LOGITS
    XmlAccessorType
    0.56
    class
    0.56
    StoryboardSegue
    0.53
    DoubleQuotes
    0.52
    AutoField
    0.52
    GraphicsUnit
    0.52
    ViewInit
    0.51
     StatefulWidget
    0.50
     GetEnumerator
    0.50
    IContainer
    0.50
    Act Density 0.089%

    No Known Activations