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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11089
    Prev
    Next
    INDEX
    Explanations

    made

    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
    AndEndTag
    -0.51
    はじめに
    -0.49
    asikan
    -0.47
     dasarnya
    -0.47
    ńczy
    -0.45
    interna
    -0.45
    REET
    -0.44
     응
    -0.44
    namentales
    -0.43
    OGND
    -0.42
    POSITIVE LOGITS
    QMetaType
    0.74
     of
    0.73
    ValueStyle
    0.64
     }{@
    0.63
     BorderLayout
    0.62
    HttpFoundation
    0.61
     breech
    0.60
     '\\;'
    0.60
     JAXB
    0.59
     lenker
    0.59
    Activations Density 0.026%

    No Known Activations