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
    59.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    words and phrases related to defining or specifying concepts and frameworks

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    󠁣
    -0.48
    󠁢
    -0.44
     ब्रेकडाउन
    -0.43
     وتسجيلات
    -0.40
     IMPORTANT
    -0.35
     unhelpful
    -0.34
     ModelExpression
    -0.34
    IMPORTANT
    -0.33
     adulte
    -0.33
    uanya
    -0.33
    POSITIVE LOGITS
    LookAnd
    0.78
    InstrumentedTest
    0.65
    setVerticalGroup
    0.60
    esModule
    0.59
    fromnode
    0.53
    basicConfig
    0.53
     CreateTagHelper
    0.52
    XmlAccessorType
    0.51
    PreExecute
    0.51
    帖最后由
    0.50
    Act Density 0.004%

    No Known Activations