© 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. 1-CLT-HP
    7. 15030
    Prev
    Next
    INDEX
    Explanations

    Scandinavian/Dutch cities/countries

    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
     Dutch
    -0.41
    ">//
    -0.40
    PageRoute
    -0.40
    niken
    -0.40
    Hé
    -0.38
     blow
    -0.38
     Tom
    -0.37
    DebuggerNonUser
    -0.36
    Jereo
    -0.35
    npm
    -0.35
    POSITIVE LOGITS
    ftagPool
    0.79
     للاسماء
    0.73
     الحره
    0.71
    ſelf
    0.71
     republics
    0.71
    WriteTagHelper
    0.69
    AccessorTable
    0.68
     Meksiku
    0.68
     supérieurs
    0.67
    
    0.66
    Activations Density 0.023%

    No Known Activations