© 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. 7001
    Prev
    Next
    INDEX
    Explanations

    references to the field of engineering

    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
     mellitus
    -0.57
    ミュ
    -0.56
     Lug
    -0.56
     avsl
    -0.56
    ESR
    -0.55
    #
    -0.55
     Sonya
    -0.54
    Tori
    -0.54
    出版年
    -0.54
    chting
    -0.54
    POSITIVE LOGITS
     engineering
    3.33
     Engineering
    3.16
    Engineering
    3.02
     ENGINEERING
    2.95
    engineering
    2.94
     engineer
    2.77
     engineers
    2.63
     Engineer
    2.52
    ENGINEERING
    2.47
    engineer
    2.45
    Activations Density 0.027%

    No Known Activations