© 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. 25341
    Prev
    Next
    INDEX
    Explanations

    references to personal roles and relationships

    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
    log
    -0.54
     exceptionnel
    -0.50
    ServiceException
    -0.49
     eignen
    -0.47
    logii
    -0.47
     समीक्षक
    -0.46
     touristique
    -0.44
     vayas
    -0.44
     religieuses
    -0.43
     arus
    -0.43
    POSITIVE LOGITS
     Akismet
    0.77
     ་་
    0.68
    elemField
    0.68
    Digit
    0.65
    ^(@)
    0.64
     Houſe
    0.64
     zvuky
    0.63
     ―――――
    0.63
     Anſ
    0.63
     Digit
    0.63
    Activations Density 0.071%

    No Known Activations