© 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. 590
    Prev
    Next
    INDEX
    Explanations

    Context/Structure

    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
     dot
    -0.44
    mox
    -0.43
    {}
    -0.43
    figcaption
    -0.41
    dot
    -0.41
    gend
    -0.40
    ${
    -0.39
    NewUrlParser
    -0.39
    hed
    -0.39
    任
    -0.39
    POSITIVE LOGITS
     and
    1.11
     réfrig
    0.74
     Roskov
    0.73
     ویکی‌پدی
    0.73
    SourceChecksum
    0.69
     échou
    0.69
     éducation
    0.68
    󠁴
    0.68
     оригіналу
    0.67
    曖昧さ回避
    0.67
    Activations Density 0.000%

    No Known Activations