© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15315
    Prev
    Next
    INDEX
    Explanations

    references to a specific Korean martial art involving strikes and weapon-like moves

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -1.01
     intptr
    -1.01
     Bioaccumulative
    -0.95
     CreateTagHelper
    -0.93
    InitVars
    -0.93
     Wikispecies
    -0.90
    ulemon
    -0.90
     viewDidLoad
    -0.89
     Paglinawan
    -0.89
     étoit
    -0.87
    POSITIVE LOGITS
     
    0.62
     F
    0.55
     B
    0.54
     L
    0.52
     Red
    0.51
     H
    0.50
     red
    0.50
     PR
    0.50
    hera
    0.49
     N
    0.48
    Activations Density 0.401%

    No Known Activations