© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74513
    Prev
    Next
    INDEX
    Explanations

    Code snippets and imports

    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
    ⓧ
    -0.77
    Obrázky
    -0.69
     يتيمه
    -0.67
    ГЛА
    -0.66
    CloseOperation
    -0.63
    MemoryWarning
    -0.63
    Tikang
    -0.62
     initComponents
    -0.61
     Мексичка
    -0.61
     autorytatywna
    -0.60
    POSITIVE LOGITS
     tham
    0.49
     Ti
    0.47
     sit
    0.46
     муніципалі
    0.46
     durs
    0.43
    Ti
    0.41
     COMMAND
    0.41
    Бахар
    0.40
     link
    0.40
     take
    0.40
    Activations Density 0.000%

    No Known Activations