© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 2576
    Prev
    Next
    INDEX
    Explanations

    references to external communication methods or protocols

    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
    Negative Logits
    WebServlet
    -0.66
    AsUp
    -0.64
    ++];
    -0.62
    InjectAttribute
    -0.59
     mẽ
    -0.58
    こんにちは
    -0.57
     ""),
    -0.55
    malink
    -0.54
     глу
    -0.54
     BoxDecoration
    -0.54
    POSITIVE LOGITS
    ="@+
    0.68
    :✨
    0.63
    WebVitals
    0.63
    èdia
    0.63
    tvguidetime
    0.56
    NameInMap
    0.55
     softening
    0.54
    GeneratedCode
    0.53
     kysy
    0.52
    THISDAY
    0.52
    Activations Density 0.110%

    No Known Activations