© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12498
    Prev
    Next
    INDEX
    Explanations

    references to multipart HTML email headers

    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
     menu
    -0.83
     Menu
    -0.83
     headers
    -0.81
    menu
    -0.79
    navbar
    -0.70
     MENU
    -0.70
    TAWA
    -0.69
    fromCharCode
    -0.68
    nav
    -0.66
     menus
    -0.66
    POSITIVE LOGITS
    Header
    2.11
     Header
    0.78
    KURZBESCHREIBUNG
    0.56
    hols
    0.54
     lie
    0.54
     Mère
    0.52
     lượt
    0.51
    getHeader
    0.49
    Keterangan
    0.48
    zis
    0.48
    Activations Density 0.002%

    No Known Activations