© 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. 2931
    Prev
    Next
    INDEX
    Explanations

    code

    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
     المعيارى
    -0.66
    adaptiveStyles
    -0.51
    PerformLayout
    -0.49
    ')['
    -0.48
     ligiloj
    -0.48
    BITMAP
    -0.47
    contd
    -0.47
     quitté
    -0.46
     kasarigan
    -0.46
    tamol
    -0.45
    POSITIVE LOGITS
    oredCriteria
    0.60
    OrEmpty
    0.54
    equalsIgnoreCase
    0.51
    jov
    0.49
    bank
    0.48
    ัพท์
    0.48
     Vict
    0.48
    ergies
    0.47
     liaison
    0.47
    tagHelperRunner
    0.47
    Activations Density 0.006%

    No Known Activations