© 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. 92742
    Prev
    Next
    INDEX
    Explanations

    Geography and naval

    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
     Royal
    -0.81
    Royal
    -0.79
     Royale
    -0.64
     ROYAL
    -0.62
     royal
    -0.58
     royale
    -0.56
    roy
    -0.55
    royal
    -0.52
    Życiorys
    -0.45
    ROY
    -0.45
    POSITIVE LOGITS
     تضيفلها
    0.84
    TargetException
    0.75
    存于互联网档案馆
    0.71
     Riproduzione
    0.71
     pleaſure
    0.70
    featureID
    0.68
    MemoryWarning
    0.68
    WillAppear
    0.68
    StoreMessageInfo
    0.68
    MigrationBuilder
    0.67
    Activations Density 1.046%

    No Known Activations