© 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. 1-RES-MATRYOSHKA-DC
    7. 264
    Prev
    Next
    INDEX
    Explanations

    references to mRNA or similar molecular constructs

    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
    ‍♀️
    -0.53
    ainville
    -0.52
    ıştı
    -0.50
    cách
    -0.49
     Tole
    -0.48
     linkovi
    -0.48
    ジュアル
    -0.47
     EDA
    -0.47
    UnusedPrivate
    -0.47
    ıyı
    -0.46
    POSITIVE LOGITS
     m
    2.95
    m
    2.95
     M
    2.42
    M
    2.30
     м
    1.91
    getM
    1.73
     М
    1.61
     getM
    1.60
    ｍ
    1.55
    М
    1.54
    Activations Density 2.180%

    No Known Activations