© 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. 3-RES-MATRYOSHKA-DC
    7. 917
    Prev
    Next
    INDEX
    Explanations

    strings of characters that look like citations, including volume numbers, page numbers, and author initials

    oai_token-act-pair · gemini-2.0-flash
    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
     even
    -0.47
     sais
    -0.47
    ärsk
    -0.45
    PreferredItem
    -0.43
     выбо
    -0.43
     lắm
    -0.41
    AssignableFrom
    -0.40
    lington
    -0.39
    spf
    -0.39
     fact
    -0.38
    POSITIVE LOGITS
     nakalista
    0.90
    Personendaten
    0.76
    mergeFrom
    0.75
     للمعارف
    0.73
     >=",
    0.70
     كومونز
    0.69
    Datuak
    0.69
     lenker
    0.65
    /*
    0.65
     发表于
    0.65
    Activations Density 0.470%

    No Known Activations