© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41843
    Prev
    Next
    INDEX
    Explanations

    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
     للمعارف
    -0.97
     مرئيه
    -0.92
     ISNI
    -0.87
     cherchés
    -0.85
     '\\;'
    -0.83
    Personensuche
    -0.81
     lenker
    -0.80
     AssemblyCulture
    -0.78
    GOTREF
    -0.75
    +#+#
    -0.75
    POSITIVE LOGITS
     responsible
    0.55
     in
    0.51
     on
    0.51
     “
    0.51
     
    0.50
     around
    0.49
     hand
    0.48
     b
    0.48
     B
    0.48
     just
    0.47
    Activations Density 0.282%

    No Known Activations