© 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. 0-CLT-HP
    7. 92927
    Prev
    Next
    INDEX
    Explanations

    SMART

    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
    s
    -0.91
     فريبيس
    -0.82
     تضيفلها
    -0.82
    SourceChecksum
    -0.80
     sedentary
    -0.78
    sit
    -0.77
     AssemblyCompany
    -0.76
     CreateTagHelper
    -0.76
    queryInterface
    -0.72
    ollectionView
    -0.71
    POSITIVE LOGITS
     c
    0.48
    <eos>
    0.47
     U
    0.44
    Razor
    0.42
    //-----
    0.41
     http
    0.41
     लेकर
    0.41
    tle
    0.40
     geslacht
    0.39
    TC
    0.39
    Activations Density 0.033%

    No Known Activations