© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43069
    Prev
    Next
    INDEX
    Explanations

    United

    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
     United
    -0.80
    United
    -0.73
     UNITED
    -0.60
     united
    -0.59
    united
    -0.59
     worldwide
    -0.57
     global
    -0.56
     compact
    -0.55
    UNITED
    -0.55
     globally
    -0.51
    POSITIVE LOGITS
    出版年
    0.80
    rungsseite
    0.77
    
    0.74
     States
    0.70
    XmlAccessType
    0.68
     Audiodateien
    0.66
    ViewImports
    0.64
    TagMode
    0.64
    SequentialGroup
    0.64
    énario
    0.64
    Activations Density 0.114%

    No Known Activations