© 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. 43751
    Prev
    Next
    INDEX
    Explanations

    threat

    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
     threat
    -2.31
    threat
    -2.27
     Threat
    -2.11
    Threat
    -2.11
     threatened
    -2.03
     threatening
    -2.00
     threaten
    -2.00
     threats
    -1.95
     Threats
    -1.76
     threatens
    -1.73
    POSITIVE LOGITS
    unknownFields
    0.62
     estimés
    0.54
     to
    0.54
    memoized
    0.50
    Referanser
    0.49
    zulegen
    0.49
     katze
    0.49
    ress
    0.47
    ing
    0.47
     Kraj
    0.46
    Activations Density 0.113%

    No Known Activations