© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15507
    Prev
    Next
    INDEX
    Explanations

    patterns involving complex mathematical expressions or notation, specifically certain types of specialized equations or symbols

    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
    LITERAL
    -0.60
    <thead>
    -0.53
     Afford
    -0.51
     Wicidata
    -0.51
     relacion
    -0.48
    uws
    -0.48
     rol
    -0.48
    Nowhere
    -0.47
    goto
    -0.47
    fax
    -0.47
    POSITIVE LOGITS
    )}(
    2.36
    )}(\
    1.17
     ExecuteAsync
    0.66
    ^(@
    0.62
     Jove
    0.59
    errHandler
    0.54
     <=",
    0.54
     مشارکت‌کنندگان
    0.54
     للاسماء
    0.53
     Gauss
    0.52
    Activations Density 0.001%

    No Known Activations