© 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. 12521
    Prev
    Next
    INDEX
    Explanations

    toxicity/exacerb

    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
     exaggeration
    -0.78
     exaggerate
    -0.73
     exagger
    -0.66
     exag
    -0.61
     exager
    -0.60
     exaggerated
    -0.59
    Spoljašnje
    -0.57
    CodedInputStream
    -0.57
     exaggerating
    -0.55
     Waray
    -0.54
    POSITIVE LOGITS
     חיצוניים
    0.71
    rungsseite
    0.66
     ujednoznacz
    0.63
    tagHelperRunner
    0.62
    :✨
    0.59
    Gön
    0.53
    Personensuche
    0.52
     فريبيس
    0.52
     ProtoMessage
    0.51
     AssemblyCulture
    0.50
    Activations Density 0.031%

    No Known Activations