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
    54.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    multi-part sentences or complex structures in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ndale
    -0.47
    loaf
    -0.44
     specialise
    -0.44
     swear
    -0.42
    lastonbury
    -0.42
     vapour
    -0.42
     cdti
    -0.42
     wield
    -0.41
     Familienname
    -0.41
    isième
    -0.41
    POSITIVE LOGITS
    LookAnd
    0.44
    webElementXpaths
    0.44
     betweenstory
    0.43
    fromnode
    0.38
    ContextHolder
    0.38
    +#+#
    0.37
    rrggbb
    0.37
     tárgy
    0.36
    PointerException
    0.36
    OGND
    0.34
    Act Density 2.775%

    No Known Activations