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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93318
    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
    tu
    -0.50
     EdgeInsets
    -0.50
    uta
    -0.50
     Ut
    -0.46
    tomans
    -0.45
    ucas
    -0.43
    ui
    -0.43
     Kean
    -0.43
     UT
    -0.42
    racite
    -0.42
    POSITIVE LOGITS
    -------------</
    0.77
     Efq
    0.76
     Chriftian
    0.75
    AndEndTag
    0.75
     pleaſure
    0.72
     itſelf
    0.70
     reaſon
    0.69
     Majefty
    0.68
     AssemblyCompany
    0.66
    ServletConfig
    0.66
    Activations Density 0.006%

    No Known Activations