© 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. 77685
    Prev
    Next
    INDEX
    Explanations

    French words

    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
    findpost
    -0.84
     nakalista
    -0.81
    IntoConstraints
    -0.79
     estekak
    -0.78
    GEBURTSDATUM
    -0.71
     defaultstate
    -0.69
    তথ্যসূত্র
    -0.69
     незавершена
    -0.69
     lenker
    -0.66
     ivelany
    -0.64
    POSITIVE LOGITS
     sauvages
    0.52
     scolaires
    0.52
     étranger
    0.52
     élas
    0.51
     spéciaux
    0.51
     étoit
    0.51
     peindre
    0.51
     colorés
    0.49
     leçons
    0.49
    étoit
    0.49
    Activations Density 0.000%

    No Known Activations