© 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. 13859
    Prev
    Next
    INDEX
    Explanations

    health

    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
     AspNetCore
    -0.59
    <bos>
    -0.57
     Vikipedi
    -0.53
    HttpFoundation
    -0.49
     opérateur
    -0.49
    izarse
    -0.48
     pem
    -0.47
     p
    -0.45
    줄
    -0.45
     ModelExpression
    -0.44
    POSITIVE LOGITS
     Efq
    0.73
     cdti
    0.69
     Walkover
    0.66
     myſelf
    0.65
     CreateTagHelper
    0.63
     doubtnut
    0.62
     againſt
    0.60
     NSCoder
    0.59
     faſt
    0.59
    Personensuche
    0.58
    Activations Density 0.066%

    No Known Activations