© 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. 0-CLT-HP
    7. 1317
    Prev
    Next
    INDEX
    Explanations

    geography, history and 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
     universe
    -1.49
     Europe
    -1.41
     Universe
    -1.30
    universe
    -1.13
    Europe
    -1.03
    Universe
    -1.01
    europe
    -0.94
     EUROPE
    -0.88
     universes
    -0.88
     UNIVER
    -0.85
    POSITIVE LOGITS
     publiques
    0.69
     suivants
    0.68
     ouvertes
    0.68
     femininas
    0.66
     humaines
    0.65
     leçons
    0.64
     larmes
    0.62
     vermelhas
    0.61
     particuliers
    0.60
     comigo
    0.60
    Activations Density 1.578%

    No Known Activations