© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6304
    Prev
    Next
    INDEX
    Explanations

    time

    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
    Negative Logits
     indépendante
    -0.71
     médicale
    -0.70
    Says
    -0.69
     égale
    -0.63
     particulières
    -0.62
    Adds
    -0.62
     médicaux
    -0.61
     particulière
    -0.60
     sanitaires
    -0.60
     différente
    -0.60
    POSITIVE LOGITS
     nakalista
    0.85
    windowFixed
    0.79
     kasarigan
    0.73
    LookAnd
    0.71
     pinulongan
    0.70
     Paglinawan
    0.69
     Normdatei
    0.69
     "..\..\..\
    0.68
    Билгалдахарш
    0.67
     TextAppearance
    0.66
    Activations Density 0.002%

    No Known Activations