© 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. 2-RES-MATRYOSHKA-DC
    7. 3816
    Prev
    Next
    INDEX
    Explanations

    references to solid samples or material in contextual scientific or technical descriptions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    koop
    -0.60
    riwal
    -0.60
    ndice
    -0.58
    Tow
    -0.57
     Leinwand
    -0.57
    annique
    -0.57
    Batter
    -0.57
     Atem
    -0.57
    wpi
    -0.57
    Lamar
    -0.56
    POSITIVE LOGITS
     solid
    3.44
    solid
    3.39
     Solid
    3.34
    Solid
    3.34
     SOLID
    2.97
    SOLID
    2.52
     sólido
    2.38
     solids
    2.30
     sólidos
    2.17
     Solids
    2.16
    Activations Density 0.019%

    No Known Activations