© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 20
    Prev
    Next
    INDEX
    Explanations

    references to specific cancer-related markers and their expressions in tissue samples

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    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
     kasarigan
    -1.05
    GEBURTSDATUM
    -0.95
    GOTREF
    -0.94
     propOrder
    -0.93
    sizeCache
    -0.93
    CppMethod
    -0.90
     ویکی‌پدی
    -0.90
     مرئيه
    -0.88
    цездатний
    -0.86
     ब्रेकडाउन
    -0.85
    POSITIVE LOGITS
     is
    0.66
     also
    0.62
     itself
    0.55
     was
    0.49
    '
    0.48
     actually
    0.48
     in
    0.48
     has
    0.47
     are
    0.46
     only
    0.46
    Activations Density 14.738%

    No Known Activations