© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14492
    Prev
    Next
    INDEX
    Explanations

    higher/lower

    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
    conazole
    -0.52
     bib
    -0.52
    logiques
    -0.47
     attitudes
    -0.47
    克拉
    -0.46
    olk
    -0.45
    itudes
    -0.45
    Kraj
    -0.43
    illeur
    -0.43
    勒
    -0.43
    POSITIVE LOGITS
     betweenstory
    0.83
     CreateTagHelper
    0.80
     للاسماء
    0.79
     nakalista
    0.76
    LookAnd
    0.75
     تضيفلها
    0.75
    хьтан
    0.73
     kaarangay
    0.70
     ویکی‌پدی
    0.69
     שוליים
    0.69
    Activations Density 0.007%

    No Known Activations