© 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. 2-RES-MATRYOSHKA-DC
    7. 3853
    Prev
    Next
    INDEX
    Explanations

    references to the "derivative" (or "differential") notation in mathematical expressions, specifically related to differentials or derivatives of ideals

    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
     CreateTagHelper
    -1.02
    LookAnd
    -0.93
    MigrationBuilder
    -0.76
    Rüyada
    -0.75
    UnusedPrivate
    -0.74
    gameserver
    -0.74
    oneofs
    -0.72
    tanleria
    -0.72
    odorant
    -0.70
    igshid
    -0.70
    POSITIVE LOGITS
    dd
    3.25
    DD
    2.86
     dd
    2.25
     DD
    2.08
    Dd
    1.27
    ddle
    1.20
    dds
    1.19
    DDD
    1.17
    ddd
    1.01
    ddling
    0.98
    Activations Density 0.023%

    No Known Activations