© 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. 10590
    Prev
    Next
    INDEX
    Explanations

    mentions of various medical and laboratory conditions or measurements

    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
    Negative Logits
    esModule
    -0.75
    PerformLayout
    -0.65
    MigrationBuilder
    -0.63
    DECREF
    -0.63
     виправивши
    -0.62
    ValueGeneration
    -0.61
    elseif
    -0.57
    terraform
    -0.57
     مشين
    -0.57
    withstanding
    -0.56
    POSITIVE LOGITS
    idemia
    2.88
    omen
    1.23
    OMEN
    1.06
     Better
    0.93
    Better
    0.88
    omena
    0.76
     Fiche
    0.54
    deri
    0.53
    BET
    0.52
    agerie
    0.52
    Activations Density 0.006%

    No Known Activations