© 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. 20-CLT-HP
    7. 77910
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.86
    ConstraintMaker
    -0.76
    GEBURTSDATUM
    -0.73
    IVEREF
    -0.72
    StructEnd
    -0.64
     continúas
    -0.64
    脚注の使い方
    -0.63
    expandindo
    -0.62
    anolamine
    -0.61
     Мексичка
    -0.61
    POSITIVE LOGITS
     utility
    0.75
    utility
    0.60
     cooling
    0.57
     heating
    0.57
     hydro
    0.52
     AC
    0.52
     Utility
    0.48
    getDoctrine
    0.47
    AC
    0.46
     utilities
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.