© 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-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 10797
    Prev
    Next
    INDEX
    Explanations

    references to medical or technical terminology related to imaging, devices, or equipment

    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
    .
    -0.50
    id
    -0.49
    -
    -0.48
    in
    -0.47
    on
    -0.47
    es
    -0.44
    en
    -0.44
    n
    -0.44
    al
    -0.41
    ense
    -0.40
    POSITIVE LOGITS
    ')));
    0.88
     AssemblyCulture
    0.88
    ',...
    0.88
    WriteBarrier
    0.88
    évaluateur
    0.87
     muualla
    0.86
    — 
    0.85
     وتسجيلات
    0.85
    """,
    0.84
    клопе
    0.84
    Activations Density 0.913%

    No Known Activations