© 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. 37
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to court proceedings

    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
    Not in Any Lists

    No Comments

    Negative Logits
     regions
    -0.53
     landscapes
    -0.53
     flavour
    -0.52
     environments
    -0.51
     models
    -0.50
     technologies
    -0.49
     gadgets
    -0.49
     horizons
    -0.49
     innovators
    -0.49
     genres
    -0.48
    POSITIVE LOGITS
     withdrew
    0.64
     alleged
    0.62
     allegedly
    0.61
     complained
    0.59
     refused
    0.54
     unlawfully
    0.54
     pleaded
    0.53
    RegressionTest
    0.53
     verbally
    0.52
     voluntarily
    0.52
    Activations Density 10.086%

    No Known Activations