© 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. 3-RES-MATRYOSHKA-DC
    7. 2132
    Prev
    Next
    INDEX
    Explanations

    text enclosed in parentheses or quotations and specific word patterns.

    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
    原始内容存档于
    -0.71
     utafitiHapana
    -0.70
    存于互联网档案馆
    -0.69
    AutoField
    -0.67
    KommentareTeilen
    -0.66
     ['./
    -0.59
    χρι
    -0.57
    CppMethod
    -0.56
    ("/:
    -0.56
    ArgsConstructor
    -0.54
    POSITIVE LOGITS
     оригіналу
    0.71
    complexContent
    0.59
    ?}",
    0.57
     résine
    0.55
     dentelle
    0.54
    IGraphics
    0.52
    êté
    0.51
    ":[{
    0.51
     larmes
    0.51
    Manbalar
    0.50
    Activations Density 1.317%

    No Known Activations