© 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. 20-CLT-HP
    7. 75128
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    WebVitals
    -0.68
     مشين
    -0.57
    muñ
    -0.55
    ptid
    -0.54
     Keyes
    -0.52
    utnik
    -0.51
    siana
    -0.51
     metron
    -0.50
     tén
    -0.50
     Fluor
    -0.50
    POSITIVE LOGITS
    niająca
    0.57
    Jeografia
    0.57
    ISupport
    0.55
     Harian
    0.50
    orsese
    0.49
     الحره
    0.49
    IContainer
    0.48
    AsUp
    0.47
     ostavi
    0.47
     akut
    0.47
    Activations Density 0.001%

    No Known Activations