© 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. 5-CLT-HP
    7. 3970
    Prev
    Next
    INDEX
    Explanations

    geographical locations

    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
    AntiForgeryToken
    -0.90
     Wicidata
    -0.85
     بيها
    -0.73
    tonsoft
    -0.73
    Personensuche
    -0.72
     EconPapers
    -0.71
     ujednoznacz
    -0.70
    enumii
    -0.69
     سكانية
    -0.68
    ]")]
    -0.68
    POSITIVE LOGITS
     række
    0.40
     two
    0.37
    ربع
    0.34
     deux
    0.33
    ława
    0.33
     dvou
    0.33
    |}{$
    0.32
     двумя
    0.32
     schimb
    0.32
    <eos>
    0.31
    Activations Density 0.001%

    No Known Activations