© 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. 0-RES-MATRYOSHKA-DC
    7. 15889
    Prev
    Next
    INDEX
    Explanations

    references to abrupt environmental or atmospheric phenomena, such as ozone depletion or holes

    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
    
    -0.78
    runApp
    -0.69
    twimg
    -0.65
    AndEndTag
    -0.60
     befre
    -0.56
    出版年
    -0.55
     Waray
    -0.55
     Wiktionnaire
    -0.55
     raiſ
    -0.55
     betra
    -0.54
    POSITIVE LOGITS
     begun
    2.09
     unfinished
    0.67
    MethodManager
    0.61
     sürd
    0.60
    addSubview
    0.58
     prosecution
    0.57
    gäng
    0.55
     communs
    0.55
     оригинала
    0.54
    substantial
    0.54
    Activations Density 0.001%

    No Known Activations