© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13955
    Prev
    Next
    INDEX
    Explanations

    notification

    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
     Notification
    -1.21
     notification
    -1.14
    Notification
    -1.09
     notifications
    -1.01
    notification
    -0.99
     Notifications
    -0.98
    Notifications
    -0.77
     notificaciones
    -0.76
    NOTIFICATION
    -0.76
     alert
    -0.75
    POSITIVE LOGITS
    tanleria
    0.65
    AddTagHelper
    0.59
    PreExecute
    0.56
    GraphicsUnit
    0.56
    GEBURTSDATUM
    0.56
    writerow
    0.54
    withIdentifier
    0.54
    ImageIcon
    0.53
     Chiapas
    0.53
    gia
    0.52
    Activations Density 0.015%

    No Known Activations