© 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. 183
    Prev
    Next
    INDEX
    Explanations

    legal terminology and formalities related to court proceedings and judgments

    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
     Fine
    -0.47
     Bac
    -0.43
    Kelebihan
    -0.41
    makaian
    -0.41
    atico
    -0.41
     fine
    -0.41
    fine
    -0.40
     Bard
    -0.40
    Fine
    -0.39
     Book
    -0.39
    POSITIVE LOGITS
     esternos
    0.64
    apimachinery
    0.59
     Vikipedi
    0.57
    httphttps
    0.57
    endphp
    0.56
    abestanden
    0.56
    -------
    0.56
     PeEnEo
    0.54
    GEBURTSDATUM
    0.53
     typelib
    0.52
    Activations Density 1.444%

    No Known Activations