© 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. 1-RES-MATRYOSHKA-DC
    7. 365
    Prev
    Next
    INDEX
    Explanations

    numerical expressions and calculations involving derivatives and algebraic formulas

    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
     rękaw
    -0.54
    teu
    -0.52
    abstractmethod
    -0.52
    enschap
    -0.50
    Eksterne
    -0.49
     współpracy
    -0.48
     rów
    -0.48
     wykona
    -0.48
    tahui
    -0.47
     ćwic
    -0.47
    POSITIVE LOGITS
     z
    3.00
     Z
    2.92
    z
    2.80
    Z
    2.78
    getZ
    2.06
    Ｚ
    1.77
    Zs
    1.67
    ｚ
    1.65
    𝑧
    1.57
     з
    1.52
    Activations Density 0.706%

    No Known Activations