© 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. 5-CLT-HP
    7. 94087
    Prev
    Next
    INDEX
    Explanations

    death

    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
    Executives
    -0.54
    HttpFoundation
    -0.52
     Logement
    -0.48
     ***!
    -0.47
     تعدى
    -0.46
    ỡng
    -0.45
     Authorities
    -0.44
    eqn
    -0.44
    uolo
    -0.43
    ewon
    -0.43
    POSITIVE LOGITS
     threats
    0.74
    SharedDtor
    0.71
     الحره
    0.65
     itself
    0.62
    ly
    0.62
     <<<<<<<<<<<<<<
    0.62
     Threats
    0.60
     lanes
    0.59
     sentences
    0.58
     <>",
    0.57
    Activations Density 0.001%

    No Known Activations