© 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. 73070
    Prev
    Next
    INDEX
    Explanations

    technical/uncommon terms

    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
     للمعارف
    -0.49
     saan
    -0.48
     transition
    -0.48
    +#+#
    -0.47
    FOOTNOTES
    -0.47
    pras
    -0.47
     Supers
    -0.47
    foon
    -0.45
     anymore
    -0.45
    fieras
    -0.44
    POSITIVE LOGITS
    Personendaten
    0.79
     resourceCulture
    0.61
    таратура
    0.61
     RoutedEventArgs
    0.54
     Paglinawan
    0.52
    alama
    0.50
    Digitized
    0.50
    EndContext
    0.50
     Joomla
    0.49
    Geplaatst
    0.48
    Activations Density 0.002%

    No Known Activations