© 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. 92223
    Prev
    Next
    INDEX
    Explanations

    Europe

    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
     Europe
    -0.82
    Europe
    -0.79
     <>",
    -0.73
    EnableWeb
    -0.69
     europe
    -0.63
    setVerticalGroup
    -0.62
    providedIn
    -0.61
    HtmlAttribute
    -0.60
     GenerationType
    -0.59
    europe
    -0.59
    POSITIVE LOGITS
     venons
    0.64
     ordinaire
    0.59
     contemporain
    0.58
     gynhyrchwyd
    0.53
     voulons
    0.52
     ordinaires
    0.52
     âgées
    0.50
     récente
    0.48
     Савезне
    0.48
     végétale
    0.48
    Activations Density 0.059%

    No Known Activations