© 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. 2-RES-MATRYOSHKA-DC
    7. 7482
    Prev
    Next
    INDEX
    Explanations

    references to a specific procedural or technical term, likely a proper noun or a named entity

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     calendriers
    -0.66
    migrationBuilder
    -0.63
    ScopeManager
    -0.61
    fato
    -0.61
     Azt
    -0.61
     tartalomajánló
    -0.60
    Scoop
    -0.60
    CreateMap
    -0.60
     déclar
    -0.59
    TypedDataSet
    -0.59
    POSITIVE LOGITS
     Tra
    3.38
    tra
    3.36
    Tra
    3.36
     tra
    3.20
     TRA
    2.33
    TRA
    2.13
     trapping
    1.82
     Тра
    1.78
     trap
    1.70
     тра
    1.70
    Activations Density 0.065%

    No Known Activations