© 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. 94068
    Prev
    Next
    INDEX
    Explanations

    code/writing

    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
    Демографія
    -0.50
     wireType
    -0.48
     venons
    -0.46
     iprot
    -0.44
     entrevist
    -0.43
     doigt
    -0.43
     Processed
    -0.43
    principalColumn
    -0.43
    antaranya
    -0.42
    processed
    -0.42
    POSITIVE LOGITS
     disambiguazione
    0.83
    KommentareTeilen
    0.72
    TagMode
    0.66
     ويكيپيديا
    0.66
    pois
    0.59
    énario
    0.59
     חיצוניים
    0.57
    quiao
    0.57
    ंदीखरीदारी
    0.54
    hpp
    0.54
    Activations Density 0.008%

    No Known Activations