© 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. 1918
    Prev
    Next
    INDEX
    Explanations

    a mix of code-related terms, mathematical symbols, product-related terms, electrical wiring terms, and chemical terms with numbers

    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
    GeneratedCode
    -0.72
    +#+
    -0.68
    PhysRevLett
    -0.66
     estekak
    -0.64
    IsContent
    -0.64
    complexContent
    -0.63
    Хьажоргаш
    -0.62
    Sucesor
    -0.61
     nakalista
    -0.61
     saites
    -0.61
    POSITIVE LOGITS
    ̈́
    0.60
    .³
    0.52
    %")
    0.48
    substack
    0.47
    SpringRunner
    0.45
    rometers
    0.44
     }}$}
    0.44
    enumi
    0.44
    .")
    0.43
    SharedDtor
    0.43
    Activations Density 2.398%

    No Known Activations