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
    69.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    concepts and terms related to programming languages and their features

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    WireFormat
    -0.45
     komis
    -0.40
     recompensa
    -0.32
    interprétation
    -0.32
     `
    -0.31
     gravedad
    -0.31
     asumi
    -0.30
     existing
    -0.30
     
    -0.30
     assumption
    -0.30
    POSITIVE LOGITS
    rrggbb
    0.66
     defaultstate
    0.60
    InjectAttribute
    0.60
    setVerticalGroup
    0.57
    ">//
    0.56
    Искәрмәләр
    0.56
    IntoConstraints
    0.55
    
    0.54
     propOrder
    0.53
    analog
    0.52
    Act Density 2.409%

    No Known Activations