© 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. 32595
    Prev
    Next
    INDEX
    Explanations

    conversational elements and transitions

    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
     below
    -0.54
    atism
    -0.50
    below
    -0.49
     désolés
    -0.49
     Voici
    -0.46
    assar
    -0.45
     Below
    -0.45
    keyColumn
    -0.44
     dettagli
    -0.44
     dettaglio
    -0.44
    POSITIVE LOGITS
     שוליים
    0.71
    ⓧ
    0.69
    FOOTNOTES
    0.68
    iseta
    0.67
    swire
    0.66
    OpenHelper
    0.66
     חיצוניים
    0.65
    DeleteBehavior
    0.63
    клопе
    0.62
    KEYCODE
    0.62
    Activations Density 0.062%

    No Known Activations