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
    49.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    proper nouns and specific terminology related to various subjects

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ➟
    -0.46
     voran
    -0.45
    SequentialGroup
    -0.45
    quiel
    -0.44
    Напомним
    -0.43
    urbed
    -0.43
     hinweg
    -0.43
    ufficio
    -0.42
    Subview
    -0.42
    naeus
    -0.42
    POSITIVE LOGITS
     HttpNotFound
    0.65
    rrggbb
    0.61
     resourceCulture
    0.57
     ligiloj
    0.43
     getUserId
    0.43
    MLLoader
    0.42
     createSlice
    0.42
    domada
    0.42
     Италијани
    0.42
     raiſ
    0.42
    Act Density 0.003%

    No Known Activations