© 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. 0-RES-MATRYOSHKA-DC
    7. 11441
    Prev
    Next
    INDEX
    Explanations

    patterns related to structural and formatting elements in text, such as specific tokens used in code or markup

    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
    الحياه
    -0.50
    :✨
    -0.49
    uttavia
    -0.49
    раздо
    -0.48
    FDR
    -0.48
    Конечно
    -0.46
    waitKey
    -0.46
    يميديا
    -0.46
    Typo
    -0.46
     HttpRequest
    -0.46
    POSITIVE LOGITS
    herence
    1.06
    BIND
    0.93
     CIS
    0.90
    dest
    0.87
    gaz
    0.80
    CIS
    0.79
    psp
    0.78
     Monfieur
    0.78
    iad
    0.76
     iterator
    0.71
    Activations Density 0.012%

    No Known Activations