© 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. 1-RES-MATRYOSHKA-DC
    7. 1305
    Prev
    Next
    INDEX
    Explanations

    statements indicating logical or consequential reasoning

    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
    ."],
    -0.54
    shadowOpacity
    -0.51
    Демографія
    -0.50
    ցված
    -0.49
    ￣)
    -0.48
     Knot
    -0.47
    :]:
    -0.47
    ؤية
    -0.47
    جغرافيا
    -0.47
    ₁)
    -0.47
    POSITIVE LOGITS
    DataAnnotations
    0.75
    何より
    0.70
     تضيفلها
    0.69
     незавершена
    0.69
     وعلى
    0.69
    GraphicsUnit
    0.68
    iprot
    0.68
     שוליים
    0.66
    principalColumn
    0.65
     فريبيس
    0.65
    Activations Density 4.479%

    No Known Activations