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
    60.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    specialized terms and symbols used in mathematical or computational contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Smarty
    -0.48
     elettrica
    -0.37
     Audiodateien
    -0.37
     ***!
    -0.36
     vapour
    -0.35
     Picchu
    -0.35
     nitrous
    -0.35
    Seznam
    -0.35
    wayat
    -0.34
    rippa
    -0.33
    POSITIVE LOGITS
    ſelves
    0.55
    fromnode
    0.55
     betweenstory
    0.54
     purpoſe
    0.54
    +#+#
    0.52
    ſelf
    0.51
    transQ
    0.48
    NOPQRST
    0.47
     desmotivaciones
    0.47
     ſta
    0.46
    Act Density 0.327%

    No Known Activations