© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15920
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or formulas related to equations in scientific or technical texts

    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
    vician
    -0.75
     extérieures
    -0.74
    ++];
    -0.73
     noDo
    -0.66
    fromnode
    -0.66
    Diweddarwch
    -0.65
    expandindo
    -0.65
     financières
    -0.65
     MERCHANTABILITY
    -0.65
    Datuak
    -0.65
    POSITIVE LOGITS
     exp
    2.72
     EXP
    0.79
     expulsion
    0.68
     expel
    0.65
     expend
    0.64
     expat
    0.64
     esp
    0.62
     expatri
    0.62
     expended
    0.60
     explan
    0.59
    Activations Density 0.001%

    No Known Activations