© 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. 96929
    Prev
    Next
    INDEX
    Explanations

    also

    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
    bolista
    -0.48
     urma
    -0.46
    出版年
    -0.45
     moze
    -0.45
    Geplaatst
    -0.45
    writeHead
    -0.44
    elemField
    -0.44
    請繼續往下閱讀
    -0.44
    glGen
    -0.44
     Waray
    -0.44
    POSITIVE LOGITS
    Personendaten
    0.71
     testimonials
    0.61
    awtextra
    0.60
    AddTagHelper
    0.58
     talks
    0.57
    RuleContext
    0.55
    COUVER
    0.54
     mention
    0.54
    ofern
    0.53
     touches
    0.53
    Activations Density 0.003%

    No Known Activations