© 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. 7209
    Prev
    Next
    INDEX
    Explanations

    references or mentions of specific file paths and system-related code

    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
    انجليز
    -0.68
     Calhoun
    -0.63
    XmlAccessorType
    -0.63
    SceneManagement
    -0.61
    ftagPool
    -0.61
     Noire
    -0.60
    WriteLiteral
    -0.59
     cherchés
    -0.59
     Innes
    -0.58
    ougou
    -0.57
    POSITIVE LOGITS
    usr
    3.53
     usr
    1.84
    USR
    1.11
    Usr
    1.02
    usst
    0.66
    usti
    0.58
     NSCoder
    0.57
    ush
    0.57
    angnya
    0.57
     وصلة
    0.56
    Activations Density 0.003%

    No Known Activations