© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 21003
    Prev
    Next
    INDEX
    Explanations

    exclamation marks and their significance in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    :
    -0.63
     TestBed
    -0.57
     publish
    -0.53
     onOptions
    -0.53
    :"",
    -0.52
    2
    -0.51
     =
    -0.50
    int
    -0.50
     &
    -0.50
    ’
    -0.50
    POSITIVE LOGITS
    MigrationBuilder
    0.96
     مشين
    0.86
     ModelExpression
    0.83
     المعيارى
    0.83
     ویکی‌پدیای
    0.82
    ="@+
    0.81
     فريبيس
    0.80
    uxxxx
    0.80
     nakalista
    0.79
     contextLoads
    0.77
    Activations Density 0.001%

    No Known Activations