© 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. 1-CLT-HP
    7. 9290
    Prev
    Next
    INDEX
    Explanations

    security

    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
     security
    -1.13
    security
    -1.02
     sécurité
    -0.98
    Security
    -0.97
     Security
    -0.93
     seguridad
    -0.92
     keamanan
    -0.86
     sikker
    -0.84
     veiligheid
    -0.82
     segurança
    -0.81
    POSITIVE LOGITS
     متعلقه
    0.56
    >--}}
    0.54
    enciales
    0.50
     WebDriverWait
    0.50
     Tch
    0.48
    WWF
    0.48
    ">//
    0.48
     tess
    0.48
    SerializedName
    0.47
    LayoutConstraint
    0.47
    Activations Density 0.106%

    No Known Activations