© 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. 2-RES-MATRYOSHKA-DC
    7. 4475
    Prev
    Next
    INDEX
    Explanations

    patterns related to LaTeX mathematical expressions and formatting commands

    oai_token-act-pair · gpt-4.1-nano
    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
    nito
    -0.61
    ECONDS
    -0.60
    зраст
    -0.59
     MonoBehaviour
    -0.55
    viers
    -0.54
    ridgeshire
    -0.54
    unjungi
    -0.52
    ži
    -0.50
     Qualification
    -0.50
    rlpool
    -0.50
    POSITIVE LOGITS
    !\!\
    3.28
    \!\
    1.17
    \!
    0.99
     ModelExpression
    0.98
     \!
    0.89
     MainAxisSize
    0.69
     intptr
    0.67
     nakalista
    0.66
    PerformLayout
    0.66
    abestanden
    0.65
    Activations Density 0.013%

    No Known Activations