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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4811
    Prev
    Next
    INDEX
    Explanations

    references to data transmission, memory management, or communication within computing systems

    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
     betweenstory
    -0.93
     ſind
    -0.91
    MessageOf
    -0.91
     iſt
    -0.88
    المناصب
    -0.84
     nahilalakip
    -0.82
     doubtnut
    -0.82
     $_(
    -0.81
    PreferredItem
    -0.80
     ―――――
    -0.79
    POSITIVE LOGITS
      
    0.64
    <eos>
    0.57
    .
    0.57
    ing
    0.55
    
    0.49
    ↵↵
    0.44
    
    0.43
    ̀nh
    0.41
       
    0.41
     difer
    0.41
    Activations Density 0.780%

    No Known Activations