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
    68
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    phrases indicating shared experiences or commonalities among people

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     hypothesis
    -0.42
    cioso
    -0.42
     REQU
    -0.42
     betek
    -0.41
    modb
    -0.41
     hydrostatic
    -0.41
    LabelTagHelper
    -0.40
     hakim
    -0.40
     theory
    -0.40
     biometric
    -0.40
    POSITIVE LOGITS
     shared
    0.74
    Shared
    0.67
    shared
    0.66
    
    0.64
     compartil
    0.63
     compartir
    0.61
     Shared
    0.60
     condiv
    0.59
     sharing
    0.57
     compartido
    0.57
    Act Density 0.000%

    No Known Activations