© 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. 43891
    Prev
    Next
    INDEX
    Explanations

    page

    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
     page
    -1.35
     Page
    -1.21
    page
    -0.94
    Page
    -0.90
     PAGE
    -0.90
    ページ
    -0.83
     página
    -0.78
     pages
    -0.77
     страницы
    -0.72
    PAGE
    -0.67
    POSITIVE LOGITS
     thermodynamics
    0.63
     archaeology
    0.63
    ########.
    0.63
     chromatographic
    0.62
     theorems
    0.60
    ApiModel
    0.59
     Segmentation
    0.59
     symmetries
    0.58
     Archaeology
    0.58
     Interpreting
    0.58
    Activations Density 0.104%

    No Known Activations