© 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. 7334
    Prev
    Next
    INDEX
    Explanations

    references to specific types of parts or components, particularly those involving parts or parts 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
    zzleHttp
    -0.88
     part
    -0.83
    ViewFeatures
    -0.83
    )");
    -0.80
    CloseOperation
    -0.78
     }}"></
    -0.78
    UnknownFields
    -0.77
     becauſe
    -0.77
     springfox
    -0.75
     مشين
    -0.73
    POSITIVE LOGITS
     parts
    2.33
    Parts
    2.22
     Parts
    2.14
    parts
    2.13
     PARTS
    2.06
    PARTS
    1.77
     partes
    1.40
     Teile
    1.28
     components
    1.00
     Teilen
    0.96
    Activations Density 0.013%

    No Known Activations