© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-RES-MATRYOSHKA-DC
    7. 820
    Prev
    Next
    INDEX
    Explanations

    a variety of proper nouns, particularly names of people, places, and organizations

    oai_token-act-pair · gemini-2.0-flash
    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
    Not in Any Lists

    No Comments

    Negative Logits
    комму
    -0.94
    ulemon
    -0.82
    theless
    -0.77
    setupUi
    -0.76
    contentLoaded
    -0.75
    BoxShadow
    -0.75
    rijfs
    -0.74
    Dyna
    -0.73
    iança
    -0.73
     monoch
    -0.73
    POSITIVE LOGITS
     Kars
    0.95
     Sark
    0.91
    ar
    0.89
    ars
    0.88
    vertx
    0.86
     ar
    0.85
    ARS
    0.85
     Harwood
    0.85
    arn
    0.83
     Mard
    0.83
    Activations Density 4.190%

    No Known Activations