© 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. 20-CLT-HP
    7. 73644
    Prev
    Next
    INDEX
    Explanations

    plays

    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
    +#+#
    -0.84
     Roskov
    -0.82
     AssemblyCulture
    -0.80
    mybatisplus
    -0.80
     ChromeDriver
    -0.79
    aarrggbb
    -0.77
    MLLoader
    -0.76
     Administrativna
    -0.75
     تضيفلها
    -0.73
    MigrationBuilder
    -0.73
    POSITIVE LOGITS
     a
    1.27
     an
    0.92
     have
    0.67
     had
    0.57
     has
    0.55
    have
    0.55
     einen
    0.54
     eine
    0.53
    มี
    0.52
     một
    0.50
    Activations Density 0.005%

    No Known Activations