© 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. 0-RES-MATRYOSHKA-DC
    7. 12063
    Prev
    Next
    INDEX
    Explanations

    references to the formalism of time-integrals and spectral integrals

    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
     estekak
    -0.61
     squadra
    -0.58
    getDoctrine
    -0.56
     torchvision
    -0.56
    Становништво
    -0.55
     TAMBÉM
    -0.55
     Autobiography
    -0.54
     clearColor
    -0.54
     razu
    -0.54
    Scho
    -0.51
    POSITIVE LOGITS
     integrals
    1.09
     inductive
    0.87
    opes
    0.85
    astéroïdes
    0.84
     phenyl
    0.77
    rops
    0.73
    wor
    0.70
    Wor
    0.70
     Integrals
    0.69
    kháu
    0.69
    Activations Density 0.003%

    No Known Activations