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
    50.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation marks and symbols

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     responsible
    -0.37
     switch
    -0.35
    ரிய
    -0.34
    )
    -0.32
     Responsible
    -0.32
     wield
    -0.32
     nawr
    -0.32
     Har
    -0.31
    logist
    -0.31
     responsable
    -0.31
    POSITIVE LOGITS
     Infórmanos
    0.78
     насељу
    0.75
    fromnode
    0.65
    LookAnd
    0.64
     transfieras
    0.63
    expandindo
    0.63
    AddHtmlAttribute
    0.62
     defaultstate
    0.62
     queſta
    0.62
     AssemblyCompany
    0.59
    Act Density 1.112%

    No Known Activations