© 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. 0-CLT-HP
    7. 2053
    Prev
    Next
    INDEX
    Explanations

    notebook

    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
     varandra
    -0.75
     consommateurs
    -0.73
     culturales
    -0.69
     männis
    -0.65
     nära
    -0.63
     חיצוניים
    -0.63
     början
    -0.62
     travailleurs
    -0.61
     brancas
    -0.61
     peines
    -0.60
    POSITIVE LOGITS
     незавершена
    0.71
    ing
    0.68
    Enllaces
    0.60
     Paglinawan
    0.58
     momo
    0.57
    ViewFeatures
    0.57
     archaeology
    0.57
    setVerticalGroup
    0.55
     Limoges
    0.54
    횟
    0.54
    Activations Density 1.698%

    No Known Activations