© 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. 3598
    Prev
    Next
    INDEX
    Explanations

    programming or IT

    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
    Datuak
    -0.78
    cadilly
    -0.75
    ConstraintMaker
    -0.72
     ***!
    -0.69
    Autoritní
    -0.66
    IntoConstraints
    -0.66
    DockStyle
    -0.64
    DoubleQuotes
    -0.61
     ivelany
    -0.61
     AssemblyCulture
    -0.60
    POSITIVE LOGITS
     large
    0.76
     countless
    0.73
     or
    0.71
     hundreds
    0.70
     huge
    0.70
     dozens
    0.70
     thousands
    0.68
     lots
    0.66
     numerous
    0.66
     enormous
    0.64
    Activations Density 0.002%

    No Known Activations