© 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. 4-CLT-HP
    7. 5057
    Prev
    Next
    INDEX
    Explanations

    Geographic locations/languages

    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
    addCriterion
    -0.74
    ScopeManager
    -0.67
    MessageOf
    -0.65
    AccessorTable
    -0.65
    WriteBarrier
    -0.62
     Roskov
    -0.61
     NSCoder
    -0.61
     فريبيس
    -0.58
    Hochspringen
    -0.58
    exitRule
    -0.57
    POSITIVE LOGITS
    orszá
    0.56
    OOTDTY
    0.54
    orsz
    0.50
     parishes
    0.48
    gató
    0.48
     Efq
    0.47
     contemporain
    0.46
    mphony
    0.46
     Govern
    0.46
     counties
    0.45
    Activations Density 0.006%

    No Known Activations