© 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. 97555
    Prev
    Next
    INDEX
    Explanations

    blog-like text

    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
    enterOuterAlt
    -0.62
    EventQueue
    -0.53
    astian
    -0.47
     komende
    -0.47
     navideño
    -0.47
     Mahomet
    -0.47
     Komunikasi
    -0.46
    boca
    -0.46
     themselves
    -0.44
    ียง
    -0.44
    POSITIVE LOGITS
     Normdatei
    0.72
     AssemblyCompany
    0.61
    OGND
    0.58
    رشف
    0.58
    (!__
    0.57
    تقاوى
    0.56
     ComVisible
    0.55
    PointerException
    0.54
    enumi
    0.54
    :✨
    0.54
    Activations Density 0.002%

    No Known Activations