© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13765
    Prev
    Next
    INDEX
    Explanations

    descriptions or references to the process of making something flat or smooth, specifically "flattening."

    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
     straight
    -0.61
     plain
    -0.54
    طاق
    -0.54
     far
    -0.53
    UrlResolution
    -0.53
    lemented
    -0.52
     Waray
    -0.52
    hmig
    -0.50
    far
    -0.49
     Grunds
    -0.48
    POSITIVE LOGITS
     flatten
    3.02
     flattened
    2.70
     flattening
    2.66
    flatten
    2.61
     Flatten
    2.13
    Flatten
    1.91
    tened
    1.17
    MENAFN
    0.75
    帖最后由
    0.73
    扁平
    0.73
    Activations Density 0.001%

    No Known Activations