© 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. 3250
    Prev
    Next
    INDEX
    Explanations

    Methods

    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
     surla
    -0.64
     ویکی‌پدیا
    -0.59
     defaultstate
    -0.59
    CppMethod
    -0.51
    onavir
    -0.47
     contextLoads
    -0.47
     ostavi
    -0.46
     <=",
    -0.46
    usermodel
    -0.45
    UnsafeEnabled
    -0.45
    POSITIVE LOGITS
    floating
    0.60
     floating
    0.55
     Grail
    0.52
    astres
    0.52
     could
    0.52
     Floating
    0.50
     would
    0.49
     réalis
    0.49
    Floating
    0.48
     terbang
    0.48
    Activations Density 0.002%

    No Known Activations