© 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. 1-CLT-HP
    7. 46092
    Prev
    Next
    INDEX
    Explanations

    Ros, sovereignty

    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
    vereignty
    -2.08
     sovereignty
    -1.30
     بيها
    -0.77
     createContext
    -0.73
    UnusedPrivate
    -0.69
    ignty
    -0.68
    WaitGroup
    -0.68
    Capítulo
    -0.67
    vereign
    -0.66
     MainAxisSize
    -0.66
    POSITIVE LOGITS
     spesa
    0.49
     relatif
    0.44
     généraux
    0.44
     skär
    0.44
    はじめに
    0.43
     expériment
    0.43
    闘
    0.43
     retrou
    0.42
     récompense
    0.42
     lieben
    0.40
    Activations Density 0.038%

    No Known Activations