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
    42.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    patterns related to coding and programming structure

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Ejercicio
    -0.35
    Smarty
    -0.34
    nextProps
    -0.33
    assertRaises
    -0.32
    DCHECK
    -0.32
    Aholisi
    -0.31
     meisten
    -0.31
     
    -0.31
    vir
    -0.31
     Brewing
    -0.30
    POSITIVE LOGITS
     betweenstory
    0.73
     propOrder
    0.71
    0.56
     Normdatei
    0.54
    ftance
    0.52
     purpoſe
    0.50
    bibfield
    0.49
     ſtand
    0.49
    BufferException
    0.48
    setVerticalGroup
    0.48
    Act Density 4.430%

    No Known Activations