© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93390
    Prev
    Next
    INDEX
    Explanations

    Florida

    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
     имеется
    -0.43
     separate
    -0.42
    াল
    -0.40
    chos
    -0.40
     Darío
    -0.40
    wara
    -0.39
     statesman
    -0.39
    如果有
    -0.39
     blacksmith
    -0.39
     sanction
    -0.39
    POSITIVE LOGITS
    <bos>
    1.18
    webElementXpaths
    1.07
    GEBURTSDATUM
    1.02
    Portail
    0.93
    цездатний
    0.89
    تقاوى
    0.87
     ویکی‌پدی
    0.83
     виправивши
    0.82
    aarrggbb
    0.80
     nahilalakip
    0.80
    Activations Density 0.003%

    No Known Activations