© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40740
    Prev
    Next
    INDEX
    Explanations

    Criminals

    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
     robbers
    -1.03
     thieves
    -1.01
     terrorists
    -0.97
     attackers
    -0.95
     CreateTagHelper
    -0.95
     scammer
    -0.94
     gunmen
    -0.92
     thief
    -0.91
     scammers
    -0.91
     insurgents
    -0.87
    POSITIVE LOGITS
     who
    0.49
    hores
    0.48
    sons
    0.45
     clear
    0.44
     engaged
    0.44
     living
    0.44
    removeClass
    0.43
     العام
    0.43
    aults
    0.42
    o
    0.42
    Activations Density 0.085%

    No Known Activations