© 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. 10482
    Prev
    Next
    INDEX
    Explanations

    references to specific gene identifiers

    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
    XmlAccessType
    -0.77
    jspx
    -0.67
    httphttps
    -0.63
    ScopeManager
    -0.60
    
    -0.59
    vastava
    -0.56
    invokeLater
    -0.56
     transfieras
    -0.56
    preduce
    -0.56
     statistik
    -0.56
    POSITIVE LOGITS
    KC
    2.97
     KC
    2.00
    kc
    1.93
     kc
    1.28
    Kc
    0.84
    KD
    0.56
    CppCodeGen
    0.53
     Kansas
    0.52
     KD
    0.49
     KANSAS
    0.49
    Activations Density 0.000%

    No Known Activations