© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90446
    Prev
    Next
    INDEX
    Explanations

    when

    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
     Frenchman
    -0.63
    himself
    -0.63
     Frenchmen
    -0.61
     getNome
    -0.61
     Giappone
    -0.60
     keskus
    -0.60
    such
    -0.59
     gräns
    -0.59
     varandra
    -0.59
     himself
    -0.58
    POSITIVE LOGITS
     you
    0.91
    
    0.73
     resourceCulture
    0.71
     kasarigan
    0.66
    TagMode
    0.61
    ChildScrollView
    0.60
    TagHelpers
    0.57
     distanciation
    0.53
    ReusableCell
    0.50
     onOptions
    0.50
    Activations Density 0.109%

    No Known Activations