Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74220
    Prev
    Next
    INDEX
    Explanations

    programming and foreign languages

    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
     EconPapers
    -0.78
    :✨
    -0.71
    onAttach
    -0.58
    all
    -0.56
    last
    -0.53
     anything
    -0.52
    /*++
    -0.52
     developed
    -0.52
     carrying
    -0.52
    ✭✭
    -0.52
    POSITIVE LOGITS
    Климат
    0.52
    RegressionTest
    0.50
     clearColor
    0.50
     bianche
    0.50
     giapp
    0.47
    runOnUiThread
    0.47
    clearInterval
    0.46
     réglable
    0.46
     jouets
    0.45
     correctes
    0.45
    Activations Density 0.001%

    No Known Activations