Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74299
    Prev
    Next
    INDEX
    Explanations

    software/code fragments

    np_max-act-logits · 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
    DockStyle
    -0.63
     kasarigan
    -0.57
    StoryboardSegue
    -0.56
     Astrology
    -0.56
     geologists
    -0.55
     docking
    -0.55
     geologist
    -0.55
     betweenstory
    -0.54
     Geologist
    -0.54
    WithIdentifier
    -0.54
    POSITIVE LOGITS
    DOCTYPE
    0.59
     محفوظة
    0.55
    />";
    0.52
     ویکی‌پدیای
    0.50
    /**
    0.49
    <caption>
    0.48
    koľvek
    0.47
     setOpen
    0.45
     betale
    0.44
    TestingModule
    0.44
    Activations Density 0.000%

    No Known Activations