© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2620
    Prev
    Next
    INDEX
    Explanations

    computer systems/programming

    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
    RegistryLite
    -0.66
    WithIdentifier
    -0.60
    SpringRunner
    -0.54
     himo
    -0.54
     ویکی‌پدی
    -0.54
     NSCoder
    -0.53
    AntiForgeryToken
    -0.53
    NameInMap
    -0.52
     surla
    -0.52
     UIKit
    -0.52
    POSITIVE LOGITS
    LLocation
    0.51
    atott
    0.50
    ckte
    0.50
    aronder
    0.50
     Space
    0.48
    =*/
    0.47
     Rouse
    0.47
    cals
    0.47
    сунок
    0.47
     space
    0.46
    Activations Density 0.004%

    No Known Activations