© 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. 5-CLT-HP
    7. 96172
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    érons
    -0.50
    charge
    -0.49
    CHARGE
    -0.48
     маса
    -0.47
     actualidad
    -0.47
     demas
    -0.47
     cifras
    -0.47
     tronco
    -0.45
    um
    -0.45
     balles
    -0.45
    POSITIVE LOGITS
    RegressionTest
    0.77
     JpaRepository
    0.72
     بيها
    0.71
     виправивши
    0.68
    buttonBar
    0.66
     kasarigan
    0.65
    __':
    0.63
    جغرافيا
    0.62
     getItemId
    0.62
    ✨:
    0.61
    Activations Density 0.003%

    No Known Activations