© 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. 1-CLT-HP
    7. 11887
    Prev
    Next
    INDEX
    Explanations

    academic texts

    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
    scrollLeft
    -0.47
     Zivil
    -0.45
    onia
    -0.43
    Osc
    -0.42
     للاسماء
    -0.42
     footnote
    -0.42
     ویکی‌پدیا
    -0.41
     footnotes
    -0.39
    kof
    -0.39
    Biographie
    -0.38
    POSITIVE LOGITS
    DockStyle
    0.77
    orghini
    0.72
    ulemon
    0.62
    epam
    0.62
     initComponents
    0.61
    breed
    0.59
    batore
    0.59
    
    0.58
    kháu
    0.58
     ActivatedRoute
    0.57
    Activations Density 0.048%

    No Known Activations