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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16221
    Prev
    Next
    INDEX
    Explanations

    math symbols

    np_max-act-logits · gemini-2.0-flash

    mathematical equations and expressions

    oai_token-act-pair · gemini-2.0-flash

    math formulas

    np_token-act-pair-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ---
    
    -0.47
     ويكيميديا
    -0.46
    uml
    -0.44
    pagestyle
    -0.44
    writerow
    -0.44
    ]<<"
    -0.43
    PhysRev
    -0.43
    mannian
    -0.42
    InstrumentedTest
    -0.42
    ễ
    -0.42
    POSITIVE LOGITS
     defaultstate
    0.72
     للاسماء
    0.69
     CreateTagHelper
    0.68
     beginnetje
    0.65
    olstadt
    0.59
    ensacola
    0.54
    icator
    0.54
    IUrlHelper
    0.52
    "}")
    0.52
    出版年
    0.52
    Activations Density 5.107%

    No Known Activations