© 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. 0-CLT-HP
    7. 95673
    Prev
    Next
    INDEX
    Explanations

    jobs and locations

    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
     Station
    -1.17
     station
    -0.84
     promotion
    -0.83
     STATION
    -0.79
    Promotion
    -0.79
     Promotion
    -0.78
    promotion
    -0.75
    Station
    -0.71
     Stations
    -0.66
     promotions
    -0.62
    POSITIVE LOGITS
     Efq
    0.79
     navideño
    0.77
     myſelf
    0.72
     Hift
    0.71
     Monfieur
    0.71
     beſt
    0.70
     Majefty
    0.69
     itſelf
    0.69
     pleaſure
    0.69
     purpoſe
    0.68
    Activations Density 0.309%

    No Known Activations