© 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. 6-RES-MATRYOSHKA-DC
    7. 274
    Prev
    Next
    INDEX
    Explanations

    square roots and mathematical expressions.

    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
    Демографія
    -0.61
     LoggerFactory
    -0.59
     AssemblyCulture
    -0.57
     ***!
    -0.56
     Deak
    -0.54
    }\|
    -0.52
     Dostupné
    -0.51
    [:,:,
    -0.51
    ("")]
    -0.50
     réaliste
    -0.50
    POSITIVE LOGITS
    WithIOException
    0.71
     MonoBehaviour
    0.62
    TargetException
    0.62
    MessageTagHelper
    0.59
     oprot
    0.57
    WriteTagHelper
    0.54
    pective
    0.54
    enterOuterAlt
    0.54
    toBeDefined
    0.54
    談社
    0.51
    Activations Density 2.610%

    No Known Activations