© 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. 0-CLT-HP
    7. 43034
    Prev
    Next
    INDEX
    Explanations

    inis

    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
    Rüyada
    -0.64
    +#+#
    -0.61
     Италијани
    -0.60
     &___
    -0.59
    RegistryLite
    -0.56
     незавершена
    -0.56
     Lockwood
    -0.56
    ThroughAttribute
    -0.55
    IGraphics
    -0.55
    wikidata
    -0.55
    POSITIVE LOGITS
     singoli
    0.59
     Audiodateien
    0.57
    deviantart
    0.55
     éché
    0.52
     réservés
    0.50
    antart
    0.49
     postale
    0.49
     elected
    0.48
     CascadeType
    0.47
     Thessal
    0.47
    Activations Density 1.609%

    No Known Activations