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. 74186
    Prev
    Next
    INDEX
    Explanations

    niche technical topics

    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
     Wikimedijinoj
    -0.75
     linkovi
    -0.67
     pellic
    -0.65
     jScrollPane
    -0.65
     الدولى
    -0.65
    methe
    -0.59
    apex
    -0.58
     trône
    -0.57
     فريبيس
    -0.57
     autorytatywna
    -0.57
    POSITIVE LOGITS
    Gent
    0.43
    FormUrlEncoded
    0.39
    diy
    0.39
     AssemblyCulture
    0.39
     stronger
    0.38
    Suara
    0.37
    medriver
    0.35
     Bhu
    0.35
    jski
    0.35
     CWE
    0.35
    Activations Density 0.000%

    No Known Activations