© 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. 45329
    Prev
    Next
    INDEX
    Explanations

    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
    Science
    -0.90
     scientist
    -0.88
     Scientist
    -0.87
    science
    -0.84
     científica
    -0.84
    Scientist
    -0.84
     Science
    -0.83
     Exacts
    -0.81
     scientifique
    -0.81
     science
    -0.81
    POSITIVE LOGITS
     guys
    0.47
     post
    0.41
    ございます
    0.40
     in
    0.40
     world
    0.40
    sizeCache
    0.40
     community
    0.38
     gezien
    0.38
     now
    0.37
    app
    0.36
    Activations Density 0.035%

    No Known Activations