© 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. 0-CLT-HP
    7. 93440
    Prev
    Next
    INDEX
    Explanations

    Russia, Japan, Science

    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
     Russian
    -1.33
     russian
    -1.15
    Russian
    -1.13
     Russia
    -1.12
     Russians
    -1.05
     Russie
    -1.02
     russa
    -0.99
     RUSS
    -0.95
    Russia
    -0.95
     russia
    -0.91
    POSITIVE LOGITS
    <bos>
    0.79
     Ta
    0.66
     v
    0.65
    enchymal
    0.58
     Pa
    0.58
     mission
    0.56
     Ka
    0.56
     V
    0.56
     Kir
    0.56
     tra
    0.55
    Activations Density 0.524%

    No Known Activations