© 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. 1-CLT-HP
    7. 14711
    Prev
    Next
    INDEX
    Explanations

    French names/places

    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
     secours
    -0.53
     réfugi
    -0.49
     ouvriers
    -0.49
     nôtre
    -0.47
     plages
    -0.47
     arrivée
    -0.47
     âgées
    -0.45
     Calabria
    -0.44
     vagues
    -0.44
     Adolfo
    -0.43
    POSITIVE LOGITS
    RegressionTest
    0.95
    GEBURTSDATUM
    0.82
    rungsseite
    0.81
    SharedDtor
    0.81
    tagHelperRunner
    0.70
     EconPapers
    0.70
    Geplaatst
    0.67
    دانشنامهٔ
    0.66
     transfieras
    0.66
     ExecuteAsync
    0.66
    Activations Density 0.049%

    No Known Activations