INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    50.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation marks and conversational cues

    New Auto-Interp
    Negative Logits
    -0.37
    )
    -0.37
     traditionally
    -0.32
     switch
    -0.32
    Literatur
    -0.30
     manual
    -0.30
    wood
    -0.30
     legis
    -0.30
     request
    -0.29
     hakim
    -0.29
    POSITIVE LOGITS
     '\\;'
    0.86
    LookAnd
    0.80
    fromnode
    0.77
     للمعارف
    0.75
    InstrumentedTest
    0.75
    PerformLayout
    0.73
     noDo
    0.71
    GEBURTS
    0.70
     betweenstory
    0.67
     queſta
    0.66
    Act Density 2.122%

    No Known Activations