© 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. 5-CLT-HP
    7. 94053
    Prev
    Next
    INDEX
    Explanations

    WiFi

    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
    Geplaatst
    -0.78
     disambiguazione
    -0.68
     كومونز
    -0.68
    ">//
    -0.67
    __':
    -0.66
     ویکی‌پدیای
    -0.66
     وتسجيلات
    -0.63
     pinulongan
    -0.62
    featureID
    -0.62
     Paglinawan
    -0.60
    POSITIVE LOGITS
     Protected
    0.76
     Direct
    0.63
     CERT
    0.61
    Protected
    0.59
     protected
    0.55
     direct
    0.52
     Bluffs
    0.51
     Certified
    0.49
     Calling
    0.49
     Regards
    0.49
    Activations Density 0.002%

    No Known Activations