© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12985
    Prev
    Next
    INDEX
    Explanations

    the presence of specific structural and positional patterns related to matrix or tensor elements in 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
    outer
    -1.64
    inner
    -1.22
    INNER
    -0.83
    Outer
    -0.79
    Билгалдахарш
    -0.61
     Outer
    -0.60
     OUTER
    -0.57
    buttonBar
    -0.54
     outer
    -0.52
     estekak
    -0.52
    POSITIVE LOGITS
     Inner
    0.72
    ScopeManager
    0.66
    brido
    0.62
    localctx
    0.59
     AssemblyCulture
    0.58
    собенно
    0.57
    BorderFactory
    0.57
     Remarque
    0.57
    первых
    0.57
     ویکی‌پدیای
    0.56
    Activations Density 0.004%

    No Known Activations