© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73025
    Prev
    Next
    INDEX
    Explanations

    Names, code, articles

    np_max-act-logits · 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
    ValueStyle
    -0.68
     culturelles
    -0.62
    Viited
    -0.60
    ArgumentParser
    -0.59
    Демографія
    -0.56
    İstinadlar
    -0.56
    WindowConstants
    -0.56
     näm
    -0.54
    grà
    -0.54
    IndentedString
    -0.53
    POSITIVE LOGITS
     compound
    0.73
    ]--;
    0.70
     Republicans
    0.66
    Admins
    0.64
     Democrats
    0.64
     Australians
    0.61
     nuns
    0.61
     Canadians
    0.59
     many
    0.58
    admins
    0.57
    Activations Density 0.000%

    No Known Activations