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
    53.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    sentences that contain discussions or references to evidence-based claims and their criticisms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     recognise
    -0.40
     recognised
    -0.38
    Jeg
    -0.38
     wield
    -0.36
     nawr
    -0.35
    veröffentlichung
    -0.35
    wood
    -0.34
     fertiliser
    -0.34
     specialise
    -0.34
     frein
    -0.33
    POSITIVE LOGITS
    setVerticalGroup
    0.64
    LookAnd
    0.63
    ſelf
    0.61
     noDo
    0.58
    ValueStyle
    0.54
     Infórmanos
    0.54
     queſta
    0.54
     wikipagina
    0.53
    ſelves
    0.52
     betweenstory
    0.52
    Act Density 2.974%

    No Known Activations