© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1562
    Prev
    Next
    INDEX
    Explanations

    в

    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
    и
    -0.76
    т
    -0.72
    у
    -0.69
    ets
    -0.66
    к
    -0.64
    б
    -0.62
    м
    -0.61
    е
    -0.60
    х
    -0.60
    OGND
    -0.58
    POSITIVE LOGITS
     تانيه
    0.66
    Vidite
    0.65
     enthal
    0.59
     Spinoza
    0.59
     المعرف
    0.58
     Kosovo
    0.57
    uesia
    0.56
    makeConstraints
    0.56
    inander
    0.56
     Mahomet
    0.55
    Activations Density 0.417%

    No Known Activations