© 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. 0-CLT-HP
    7. 97159
    Prev
    Next
    INDEX
    Explanations

    code/technical language

    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
    ual
    -0.48
     Hege
    -0.47
    Бра
    -0.41
    嘗
    -0.40
     Nazar
    -0.40
     Vou
    -0.40
     ital
    -0.40
    IONAL
    -0.40
     Kathmandu
    -0.40
     Lode
    -0.40
    POSITIVE LOGITS
    SourceChecksum
    0.96
    windowFixed
    0.79
     насељу
    0.74
    mybatisplus
    0.73
    पया
    0.72
    setupUi
    0.72
     nahilalakip
    0.71
    bcryptjs
    0.71
    intios
    0.69
    OGND
    0.68
    Activations Density 1.847%

    No Known Activations