© 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. 76927
    Prev
    Next
    INDEX
    Explanations

    French language

    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
    AddHtmlAttribute
    -0.62
    asking
    -0.60
     asking
    -0.57
     questioning
    -0.55
    inghouse
    -0.52
    getDoctrine
    -0.51
     liking
    -0.50
     parallelogram
    -0.49
     calling
    -0.47
    BagConstraints
    -0.46
    POSITIVE LOGITS
     sélectionnés
    0.63
     réparation
    0.60
     fidé
    0.59
     étoient
    0.59
     mères
    0.58
     auroit
    0.58
     avoient
    0.57
     démocr
    0.57
     suiv
    0.56
     ainfi
    0.56
    Activations Density 0.002%

    No Known Activations