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. 11062
    Prev
    Next
    INDEX
    Explanations

    tutorial

    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
     tutorial
    -1.48
     Tutorial
    -1.45
    Tutorial
    -1.29
    tutorial
    -1.20
    etal
    -0.82
    utorial
    -0.82
    ngdoc
    -0.76
     TUT
    -0.72
    教程
    -0.69
     tutorials
    -0.66
    POSITIVE LOGITS
    sphase
    0.57
    ed
    0.52
    WidgetItem
    0.45
     FontFamily
    0.44
    skosten
    0.43
    setContentView
    0.43
     zvuky
    0.42
     Wiktionnaire
    0.42
    simage
    0.42
    __':
    
    0.42
    Activations Density 0.013%

    No Known Activations