© 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. 0-CLT-HP
    7. 92537
    Prev
    Next
    INDEX
    Explanations

    science, technology

    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
    !*\
    -0.79
     humaines
    -0.53
     naturels
    -0.46
    compiled
    -0.45
    Secretary
    -0.44
    usercontent
    -0.44
     Secretary
    -0.43
     segre
    -0.43
     génie
    -0.43
    olahan
    -0.42
    POSITIVE LOGITS
     विश्वसनीयता
    0.67
    HtmlAttribute
    0.62
    FundMe
    0.62
    ịp
    0.58
    __":
    0.57
     useAppContext
    0.56
     Nimbus
    0.56
    principalColumn
    0.56
     Naam
    0.56
    NTIS
    0.55
    Activations Density 0.077%

    No Known Activations