© 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. 2-RES-MATRYOSHKA-DC
    7. 2691
    Prev
    Next
    INDEX
    Explanations

    gene alterations and abnormalities associated with cancer

    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
    ///</
    -0.66
     незавершена
    -0.57
     CWE
    -0.57
    ἶ
    -0.56
     Olga
    -0.52
     ilmiah
    -0.52
    этому
    -0.51
    ânea
    -0.51
    </
    -0.49
    ings
    -0.48
    POSITIVE LOGITS
    zbęd
    0.64
    ervous
    0.60
    zzini
    0.59
    undred
    0.59
     وتسجيلات
    0.59
    uests
    0.58
    SpringRunner
    0.58
    thmetic
    0.57
    rendon
    0.57
    ')['
    0.57
    Activations Density 0.060%

    No Known Activations