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
    65.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to class definitions in programming or object-oriented terms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.50
    GEBURTS
    -0.48
    wußt
    -0.45
    zeitige
    -0.44
     gemeint
    -0.41
     intptr
    -0.40
     samym
    -0.40
     garantiert
    -0.39
     beantworten
    -0.39
     Probably
    -0.39
    POSITIVE LOGITS
    XmlAccessorType
    0.59
    class
    0.55
     classes
    0.54
     class
    0.53
     createSlice
    0.52
    clase
    0.50
    parsedMessage
    0.50
    transQ
    0.50
     CLASS
    0.50
    Rosen
    0.49
    Act Density 0.001%

    No Known Activations