© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75681
    Prev
    Next
    INDEX
    Explanations

    Germany/German

    np_max-act-logits · 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
     Nepali
    -0.78
     Chilean
    -0.76
     Indonesian
    -0.76
    Thai
    -0.73
    Spanish
    -0.72
     brazilian
    -0.71
     korean
    -0.71
     Israeli
    -0.71
     Colombian
    -0.71
    Israeli
    -0.70
    POSITIVE LOGITS
     Ger
    0.57
     Germany
    0.56
    Ger
    0.55
    德
    0.54
     Germ
    0.51
     ger
    0.49
    Гер
    0.49
    ger
    0.47
    ValueStyle
    0.45
     德
    0.44
    Activations Density 0.006%

    No Known Activations