© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 2507
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "M" with the highest activation levels, indicating it detects the presence of "M" as a key feature

    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
    Negative Logits
    m
    -0.78
     m
    -0.73
    Transkript
    -0.67
    NameInMap
    -0.67
    mC
    -0.65
    AddTagHelper
    -0.64
    例文帳に追加
    -0.61
    mR
    -0.61
    IsContent
    -0.60
    XmlAccessorType
    -0.60
    POSITIVE LOGITS
    M
    1.80
     M
    1.56
    getM
    1.09
    𝑀
    1.07
    pM
    1.02
     getM
    1.01
     М
    0.99
    iM
    0.92
    Ｍ
    0.91
    М
    0.91
    Activations Density 0.087%

    No Known Activations