© 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
    2. Gemma-2-2B
    3. 2-RES-MATRYOSHKA-DC
    4. 3075
    Prev
    Next
    INDEX
    Explanations

    numerical expressions and mathematical notation

    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
    ագրություններ
    -0.82
    XmlAccessType
    -0.75
    apimachinery
    -0.63
     comuniques
    -0.62
    Vidite
    -0.61
     affichés
    -0.61
     مشين
    -0.59
     nettoy
    -0.57
     JpaRepository
    -0.56
    gridx
    -0.56
    POSITIVE LOGITS
    )/
    1.97
    ]/
    1.26
    ))/
    1.13
    ])/
    0.98
    }/
    0.94
    +)/
    0.90
    "]/
    0.65
    )/(
    0.63
    "/
    0.63
     HttpServlet
    0.60
    Activations Density 0.041%

    No Known Activations