© 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. 4215
    Prev
    Next
    INDEX
    Explanations

    references to the concept of dark matter

    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
    alanya
    -0.52
    osoever
    -0.50
    googleapis
    -0.50
    ा
    -0.49
    tyfik
    -0.48
    alanta
    -0.47
     ویکی‌پدیای
    -0.46
    oxone
    -0.46
    溢
    -0.46
    Рис
    -0.46
    POSITIVE LOGITS
     dark
    3.34
     Dark
    3.13
    dark
    3.09
    Dark
    3.03
     DARK
    2.91
    DARK
    2.64
     darker
    2.39
     darkest
    2.38
     darkness
    2.17
     oscuro
    2.11
    Activations Density 0.022%

    No Known Activations