© 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. 6167
    Prev
    Next
    INDEX
    Explanations

    patterns related to serialized structural data, such as protobuf message definitions and descriptors

    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
    出版年
    -0.68
    byshev
    -0.61
    batore
    -0.60
     NSCoder
    -0.59
    ?>">
    -0.56
    vernight
    -0.56
    käse
    -0.56
    regas
    -0.56
    VersionUID
    -0.55
    BIDDEN
    -0.54
    POSITIVE LOGITS
    SharedDtor
    0.79
     الرياضيه
    0.62
    EndInit
    0.62
    migrationBuilder
    0.60
    MigrationBuilder
    0.59
     CreateTagHelper
    0.59
    GTCX
    0.58
    useEffect
    0.58
    IMPORTED
    0.57
    SourceChecksum
    0.56
    Activations Density 0.233%

    No Known Activations