© 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. 5-CLT-HP
    7. 97342
    Prev
    Next
    INDEX
    Explanations

    Safety/Violence

    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
     Measures
    -0.73
     measures
    -0.68
    Measures
    -0.61
     mesures
    -0.57
     MEASURES
    -0.54
    maßnahmen
    -0.53
    measures
    -0.53
     Measure
    -0.50
     measure
    -0.49
    BeforeAll
    -0.49
    POSITIVE LOGITS
     تانيه
    0.70
     صوتيه
    0.60
     فريبيس
    0.59
    Personensuche
    0.53
    Biographie
    0.53
     relazioni
    0.53
    setLayout
    0.52
    jmniej
    0.52
    stream
    0.51
    BorderStyle
    0.51
    Activations Density 0.010%

    No Known Activations