© 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. 5-CLT-HP
    7. 97366
    Prev
    Next
    INDEX
    Explanations

    data description

    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
     
    -0.55
    ALLOC
    -0.51
    :
    -0.50
     slightly
    -0.47
     (
    -0.47
     largely
    -0.46
     Watch
    -0.46
     that
    -0.46
     Herr
    -0.45
     Allgemeine
    -0.44
    POSITIVE LOGITS
    Portale
    0.70
    providedIn
    0.68
    )];
    0.68
    URLException
    0.68
    COUVER
    0.67
    ergies
    0.64
    IGraphics
    0.64
    تقاوى
    0.63
     externes
    0.61
     EconPapers
    0.60
    Activations Density 0.012%

    No Known Activations