© 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. 5-CLT-HP
    7. 96524
    Prev
    Next
    INDEX
    Explanations

    defending

    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
     defend
    -0.90
     defends
    -0.84
     defended
    -0.81
     defending
    -0.76
     Defend
    -0.71
     against
    -0.59
    Def
    -0.56
     défend
    -0.56
     defensively
    -0.55
     DEFEND
    -0.53
    POSITIVE LOGITS
    IntoConstraints
    1.16
    
    0.96
    +#+#
    0.96
    OGND
    0.95
    Datuak
    0.90
     архивлан
    0.90
     Infórmanos
    0.89
     تضيفلها
    0.86
     للاسماء
    0.86
    +:+
    0.85
    Activations Density 0.006%

    No Known Activations