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
    53
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to programming concepts and code structure

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Murphy
    -0.33
    mm
    -0.32
    סף
    -0.32
    Literatur
    -0.32
    теля
    -0.31
     
    -0.31
    )
    -0.31
    wood
    -0.31
     fama
    -0.31
     vapour
    -0.30
    POSITIVE LOGITS
    ſelf
    0.69
     betweenstory
    0.68
    fromnode
    0.67
     Infórmanos
    0.66
     AssemblyCompany
    0.63
    setVerticalGroup
    0.60
     desmotivaciones
    0.59
    LookAnd
    0.59
    InstrumentedTest
    0.58
    ſelves
    0.55
    Act Density 3.381%

    No Known Activations