© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 449
    Prev
    Next
    INDEX
    Explanations

    words indicating quantity or determination

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    queles
    -0.66
     Grüsse
    -0.57
     identité
    -0.57
     wzglę
    -0.56
     læng
    -0.56
     perfección
    -0.56
     intenção
    -0.56
     obligación
    -0.55
     generazione
    -0.54
     rând
    -0.54
    POSITIVE LOGITS
     a
    1.44
     an
    1.02
     isang
    0.78
     একটি
    0.78
     another
    0.77
     μια
    0.75
     ஒரு
    0.75
     einem
    0.73
    einen
    0.71
     einer
    0.69
    Activations Density 3.437%

    No Known Activations