© 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. 12-RES-MATRYOSHKA-DC
    7. 16484
    Prev
    Next
    INDEX
    Explanations

    references to North Korea and its leaders, specifically Kim Jong Un and Kim Jong Il

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LogFactory
    -0.66
     privilégi
    -0.63
     Vikipedi
    -0.60
    مصادر
    -0.57
     defaultstate
    -0.56
    šinou
    -0.56
     تانيه
    -0.54
     sauvages
    -0.53
     rencontr
    -0.53
    Claw
    -0.53
    POSITIVE LOGITS
     Pyongyang
    1.13
    ongyang
    1.02
     DPR
    0.93
     Jong
    0.87
     Cuban
    0.79
    Jong
    0.77
     Fidel
    0.71
    Cuban
    0.71
     cigars
    0.69
     cuban
    0.69
    Activations Density 0.003%

    No Known Activations