© 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. 0-CLT-HP
    7. 95338
    Prev
    Next
    INDEX
    Explanations

    well

    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
     well
    -1.26
     Well
    -0.83
    Well
    -0.73
    well
    -0.71
     bien
    -0.64
     WELL
    -0.60
     as
    -0.52
     
    -0.50
     also
    -0.49
     wohl
    -0.45
    POSITIVE LOGITS
     незавершена
    1.09
    клопе
    1.02
     يتيمه
    1.02
     Shakspeare
    0.98
     للاسماء
    0.97
    GEBURTSDATUM
    0.96
     lenker
    0.95
    rungsseite
    0.94
    bows
    0.94
     Shaksp
    0.94
    Activations Density 0.051%

    No Known Activations