© 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. 1238
    Prev
    Next
    INDEX
    Explanations

    a mix of place names, types of materials, and mathematical symbols

    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
     Moriarty
    -0.83
     Garcia
    -0.69
     Doherty
    -0.69
    thyst
    -0.67
    ulatus
    -0.66
    vergne
    -0.66
    ieve
    -0.65
     bengal
    -0.65
     λ
    -0.64
    setData
    -0.64
    POSITIVE LOGITS
     RQ
    1.02
    AccessorTable
    1.01
    tau
    1.00
     Tapes
    0.99
     Bolton
    0.93
    ynchronously
    0.91
     ***!
    0.90
     Tape
    0.90
     dynamite
    0.87
     Dinah
    0.87
    Activations Density 4.369%

    No Known Activations