© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 191
    Prev
    Next
    INDEX
    Explanations

    vulnerable people

    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
     vulnerability
    -0.94
     vulnerable
    -0.90
    vul
    -0.80
     vulnerabilities
    -0.70
     Vulnerable
    -0.69
     Vulnerability
    -0.66
     fragile
    -0.65
    Vul
    -0.64
     weak
    -0.60
    脆弱
    -0.60
    POSITIVE LOGITS
     morire
    0.80
     scolaire
    0.78
     betweenstory
    0.75
     polaire
    0.74
    hyrchwyd
    0.71
     panoramique
    0.71
     stället
    0.68
     scolaires
    0.67
     onOptions
    0.65
     photolibrary
    0.65
    Activations Density 0.003%

    No Known Activations