© 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. 1-RES-MATRYOSHKA-DC
    7. 1420
    Prev
    Next
    INDEX
    Explanations

    the main concepts or primary subject matter of the text

    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
    XmlAccessType
    -0.59
    ModelSerializer
    -0.56
     noDo
    -0.55
    tangentMode
    -0.53
     móveis
    -0.52
     Treff
    -0.52
    省市镇
    -0.52
     crimen
    -0.50
     spécialistes
    -0.50
    memoized
    -0.49
    POSITIVE LOGITS
     main
    4.69
    main
    4.38
    Main
    4.16
     Main
    4.16
     MAIN
    3.84
    MAIN
    3.77
    getMain
    2.59
    メイン
    2.55
     głów
    2.55
     mains
    2.53
    Activations Density 0.496%

    No Known Activations