© 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-CLT-HP
    7. 95682
    Prev
    Next
    INDEX
    Explanations

    rules, laws or regulations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     requirements
    -1.33
    requirements
    -1.07
     contributions
    -1.05
     requirement
    -1.04
     commitments
    -1.03
     commitment
    -0.98
     restrictions
    -0.97
     constraints
    -0.96
     efforts
    -0.93
    ConstraintMaker
    -0.89
    POSITIVE LOGITS
     made
    0.77
     of
    0.67
     jueces
    0.63
     متعلقه
    0.60
     genoux
    0.59
     réfugiés
    0.59
     similaires
    0.56
     particuliers
    0.56
     délais
    0.56
     giud
    0.55
    Activations Density 0.046%

    No Known Activations