© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42024
    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
     للاسماء
    -0.87
    Personensuche
    -0.79
     ब्रेकडाउन
    -0.75
    sidemargin
    -0.75
    StoryboardSegue
    -0.72
    fromnode
    -0.71
     initComponents
    -0.70
    Datuak
    -0.69
    CppMethod
    -0.69
    Numerology
    -0.69
    POSITIVE LOGITS
     threats
    0.56
     Threats
    0.55
    europa
    0.53
     &[
    0.52
     threat
    0.50
    threat
    0.50
     conservation
    0.50
    Threat
    0.49
     Threat
    0.48
     given
    0.48
    Activations Density 0.094%

    No Known Activations