© 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. 1-CLT-HP
    7. 13575
    Prev
    Next
    INDEX
    Explanations

    with

    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
     cope
    -0.58
     phép
    -0.51
    adjusted
    -0.49
    httphttps
    -0.48
    ollett
    -0.48
     disesuaikan
    -0.48
    ográfico
    -0.46
    inheritDoc
    -0.46
     oignons
    -0.46
     Drittan
    -0.45
    POSITIVE LOGITS
    PerformLayout
    0.89
     nahilalakip
    0.73
    клопе
    0.73
    WaitGroup
    0.72
    BagLayout
    0.71
    IntoConstraints
    0.66
    Tembelea
    0.65
    Referencer
    0.62
     playing
    0.62
     Signor
    0.62
    Activations Density 0.034%

    No Known Activations