© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3005
    Prev
    Next
    INDEX
    Explanations

    French text

    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
     du
    -0.58
     aux
    -0.55
     des
    -0.50
    mé
    -0.47
     pour
    -0.47
    aux
    -0.47
     Drapeau
    -0.43
    É
    -0.43
    hou
    -0.43
     de
    -0.42
    POSITIVE LOGITS
     Theſe
    0.88
     ainfi
    0.87
     fédé
    0.82
     <=",
    0.81
     asiatique
    0.81
     fidé
    0.81
     acrylique
    0.81
     abstrait
    0.80
     rechange
    0.79
     recev
    0.77
    Activations Density 0.006%

    No Known Activations