© 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. 4-CLT-HP
    7. 504
    Prev
    Next
    INDEX
    Explanations

    to

    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
    tvguidetime
    -0.76
     iprot
    -0.74
     nahilalakip
    -0.72
    SharedDtor
    -0.67
    ValueStyle
    -0.66
    InjectAttribute
    -0.64
    UserScript
    -0.63
     виправивши
    -0.63
    parsedMessage
    -0.63
     незавершена
    -0.61
    POSITIVE LOGITS
     
    0.59
    1
    0.53
     fédé
    0.47
     irré
    0.47
     investissements
    0.44
     May
    0.43
     blessés
    0.43
    lección
    0.40
     supplémentaires
    0.40
     définiti
    0.40
    Activations Density 0.142%

    No Known Activations