© 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. 1455
    Prev
    Next
    INDEX
    Explanations

    safety

    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
     safety
    -2.31
    safety
    -2.19
    Safety
    -2.11
     Safety
    -2.00
     SAFETY
    -1.87
    SAFETY
    -1.56
     veiligheid
    -1.41
    afety
    -1.32
     sécurité
    -1.23
    Sicherheit
    -1.16
    POSITIVE LOGITS
    viewDidLoad
    0.45
    的第一
    0.45
    appara
    0.44
     measures
    0.43
     features
    0.41
     codes
    0.41
     for
    0.40
     since
    0.40
    forKey
    0.40
    seud
    0.40
    Activations Density 0.064%

    No Known Activations