© 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. 174
    Prev
    Next
    INDEX
    Explanations

    Storyboard

    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
    mybatisplus
    -0.60
     hers
    -0.54
    BeanUtils
    -0.54
    nestjs
    -0.53
    Географи
    -0.52
    뀝
    -0.52
     بيها
    -0.52
    DropTable
    -0.51
    Pha
    -0.51
     Pha
    -0.49
    POSITIVE LOGITS
     AssemblyCulture
    0.71
    aarrggbb
    0.66
    تقاوى
    0.59
     noDo
    0.53
     himo
    0.50
    DIPSETTING
    0.50
     EconPapers
    0.50
    \}_{
    0.48
     surla
    0.47
    \|_{
    0.45
    Activations Density 1.198%

    No Known Activations