© 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. 4424
    Prev
    Next
    INDEX
    Explanations

    references to extreme conditions or phenomena

    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
    zewod
    -0.61
    nodoc
    -0.59
    zyms
    -0.58
    Smaller
    -0.57
     Bourgoin
    -0.57
     Llew
    -0.56
    Domestic
    -0.55
    inguém
    -0.55
     ")";
    -0.55
    Hush
    -0.55
    POSITIVE LOGITS
     extreme
    2.50
    extreme
    2.31
     Extreme
    2.28
    Extreme
    2.27
     extrême
    1.98
     extre
    1.77
     extremes
    1.74
     ekst
    1.73
     extremo
    1.57
    extrême
    1.55
    Activations Density 0.019%

    No Known Activations