© 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. 72876
    Prev
    Next
    INDEX
    Explanations

    Non-English text

    np_max-act-logits · 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
    DoubleQuotes
    -0.61
     recogni
    -0.60
     jus
    -0.59
    +#+#
    -0.59
     utafiti
    -0.58
     parli
    -0.53
     oblivion
    -0.52
     berea
    -0.52
     parenchyma
    -0.52
     resourceCulture
    -0.52
    POSITIVE LOGITS
     blessés
    0.61
     âmes
    0.60
     larmes
    0.59
     pauvres
    0.57
     चीज़ों
    0.57
     dieux
    0.56
     épaules
    0.56
    THINGS
    0.56
     amarillas
    0.54
     prisonniers
    0.54
    Activations Density 0.001%

    No Known Activations