© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 7081
    Prev
    Next
    INDEX
    Explanations

    structures or features that are essential or characteristic within a specialized context

    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
    [](
    -0.55
    createCell
    -0.54
    Extinguishing
    -0.54
    nextProps
    -0.54
     Brazilian
    -0.52
    writerow
    -0.51
     Schreib
    -0.50
    sobí
    -0.49
     smooth
    -0.48
     Argent
    -0.48
    POSITIVE LOGITS
     key
    1.27
     cornerstone
    1.13
     klucz
    1.09
     pivotal
    1.05
    關鍵
    1.00
     ключе
    0.98
     keystone
    0.96
     Schlüssel
    0.94
    关键
    0.93
     crucial
    0.93
    Activations Density 0.562%

    No Known Activations