© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12368
    Prev
    Next
    INDEX
    Explanations

    utility

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Utility
    -0.93
    Utility
    -0.91
    utility
    -0.83
     utility
    -0.80
     Thessal
    -0.64
    Utilities
    -0.58
     Utilities
    -0.57
    esy
    -0.56
    rayal
    -0.56
    UTIVE
    -0.55
    POSITIVE LOGITS
     concorso
    0.67
     popoli
    0.61
    UnknownFieldSet
    0.59
     orologio
    0.59
     löyty
    0.57
     catálogo
    0.56
     catalogo
    0.56
     calculer
    0.56
     ladr
    0.55
     regresó
    0.54
    Activations Density 0.040%

    No Known Activations