© 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. 3554
    Prev
    Next
    INDEX
    Explanations

    patterns involving complex mathematical notation and LaTeX syntax

    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
    afficheront
    -0.75
    DockStyle
    -0.67
    Tagged
    -0.61
    Dow
    -0.60
     Bleeding
    -0.60
    LayoutStyle
    -0.59
     Fool
    -0.59
     chi̍t
    -0.59
     Dow
    -0.56
    elemField
    -0.56
    POSITIVE LOGITS
    plotlib
    0.53
    ības
    0.53
    }}}}
    0.52
    ulitis
    0.52
     Мексичка
    0.49
    letzt
    0.49
    Spoljašnje
    0.49
     StatelessWidget
    0.49
    IBILITIES
    0.48
     himo
    0.48
    Activations Density 0.708%

    No Known Activations