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. 12891
    Prev
    Next
    INDEX
    Explanations

    used

    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
     to
    -0.78
     nahilalakip
    -0.63
     hâte
    -0.62
     vendus
    -0.62
     medlemmer
    -0.58
     larmes
    -0.58
     difficultés
    -0.58
     chiaramente
    -0.56
     lágrimas
    -0.56
     puisse
    -0.55
    POSITIVE LOGITS
     AssemblyTitle
    0.86
     &___
    0.69
     CreateTagHelper
    0.61
     समीक्षाओं
    0.59
    
    0.58
    IBOutlet
    0.57
    AccessorTable
    0.56
    .*")]
    0.56
     productive
    0.53
    ++
    
    0.53
    Activations Density 0.053%

    No Known Activations