© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72124
    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
    queryInterface
    -0.66
    ByVersion
    -0.63
    mybatisplus
    -0.63
     NSCoder
    -0.61
    Espèce
    -0.61
    GEBURTSDATUM
    -0.59
    InstrumentedTest
    -0.59
    parsedMessage
    -0.58
     GenerationType
    -0.57
    VIAF
    -0.52
    POSITIVE LOGITS
    ampung
    0.58
     gestellt
    0.54
    #![
    0.53
    Suivez
    0.51
     puertos
    0.50
     suivez
    0.50
     idées
    0.50
    Erreferentziak
    0.50
     sélectionnés
    0.48
     définiti
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.