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. 22-CLT-HP
    4. 74308
    Prev
    Next
    INDEX
    Explanations

    code/database entries

    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
    WriteAttribute
    -0.66
    ürtel
    -0.54
    راتيج
    -0.54
     الدولى
    -0.53
    ijuana
    -0.52
    printStackTrace
    -0.51
     linkovi
    -0.50
    Witam
    -0.50
     okuyayım
    -0.50
    component
    -0.49
    POSITIVE LOGITS
    раздо
    0.58
     goma
    0.46
    Heap
    0.46
     Heap
    0.46
     StatelessWidget
    0.46
     Hentet
    0.45
     sted
    0.45
    DrawerToggle
    0.44
     numberOfRows
    0.43
    ásra
    0.43
    Activations Density 0.000%

    No Known Activations