© 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. 0-CLT-HP
    7. 44068
    Prev
    Next
    INDEX
    Explanations

    titles

    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
     titles
    -2.67
     Titles
    -2.66
    Titles
    -2.19
     Title
    -2.05
    titles
    -2.02
     títulos
    -1.93
     title
    -1.92
    Title
    -1.85
     TITLE
    -1.84
    TITLE
    -1.77
    POSITIVE LOGITS
    قایناقلار
    0.64
    writeFieldEnd
    0.59
    styleType
    0.59
    esModule
    0.57
    Зноскі
    0.56
    terus
    0.56
    PageRoute
    0.55
     sessionFactory
    0.54
     Мексичка
    0.54
    orteur
    0.52
    Activations Density 0.144%

    No Known Activations