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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96464
    Prev
    Next
    INDEX
    Explanations

    to or in

    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
    DotNetBar
    -0.69
    SPATH
    -0.63
    mybatisplus
    -0.60
     LUMP
    -0.57
     оригіналу
    -0.57
    リング
    -0.56
    Portail
    -0.56
     Inflate
    -0.56
    RegressionTest
    -0.55
    MIDDLEWARE
    -0.54
    POSITIVE LOGITS
     better
    0.77
     improved
    0.76
     increased
    0.71
     greater
    0.65
     healthier
    0.62
     happier
    0.57
     clearer
    0.56
     feeling
    0.56
     enjoying
    0.55
    better
    0.54
    Activations Density 0.002%

    No Known Activations