© 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. 20-CLT-HP
    7. 76397
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · 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
    rrggbb
    -0.71
    GEBURTSDATUM
    -0.71
    出版年
    -0.68
    RTEE
    -0.67
    InjectAttribute
    -0.66
    Życiorys
    -0.64
     cherchés
    -0.64
    :][
    -0.64
     onCreateView
    -0.63
     Earthquake
    -0.63
    POSITIVE LOGITS
    WaitGroup
    0.50
    Pautan
    0.48
     Information
    0.43
    Storage
    0.43
     Sem
    0.42
    Information
    0.41
     Storage
    0.41
     maat
    0.40
     Displays
    0.40
     bilgi
    0.40
    Activations Density 0.000%

    No Known Activations