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. 12876
    Prev
    Next
    INDEX
    Explanations

    those

    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
    rungsseite
    -0.98
     متعلقه
    -0.82
    脚注の使い方
    -0.79
     beginnetje
    -0.77
    expandindo
    -0.76
     RoutedEventArgs
    -0.74
    StoryboardSegue
    -0.74
     Мексичка
    -0.73
     BoxDecoration
    -0.72
     chré
    -0.72
    POSITIVE LOGITS
     He
    0.47
    GV
    0.45
    "]();
    0.40
     Scriptures
    0.39
    esModule
    0.38
     
    0.38
     trinh
    0.38
     lay
    0.37
     men
    0.37
    etero
    0.36
    Activations Density 0.004%

    No Known Activations