© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42673
    Prev
    Next
    INDEX
    Explanations

    European

    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
     European
    -2.20
    European
    -2.03
     Europe
    -1.88
    Europe
    -1.78
     european
    -1.76
     EUROPEAN
    -1.71
     Europeans
    -1.65
     europe
    -1.64
    EUROPEAN
    -1.55
     europea
    -1.54
    POSITIVE LOGITS
    LookAnd
    0.89
     betweenstory
    0.83
    AndEndTag
    0.82
     disambiguazione
    0.82
    Geplaatst
    0.79
     OFDb
    0.78
    Personendaten
    0.77
    IUrlHelper
    0.77
     Савезне
    0.76
     "..\..\..\
    0.76
    Activations Density 0.419%

    No Known Activations