© 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. 40393
    Prev
    Next
    INDEX
    Explanations

    culture

    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
     opera
    -1.11
     Opera
    -1.01
    Geplaatst
    -0.88
     Normdatei
    -0.75
     milking
    -0.75
    Opera
    -0.74
    esgue
    -0.73
    
    -0.72
    DockStyle
    -0.71
    MLLoader
    -0.71
    POSITIVE LOGITS
     mej
    0.44
    相互
    0.41
    bild
    0.40
     saken
    0.40
     impreso
    0.39
    isas
    0.38
    際
    0.37
    Wahl
    0.37
    oneofs
    0.36
     Inter
    0.36
    Activations Density 0.159%

    No Known Activations