© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5297
    Prev
    Next
    INDEX
    Explanations

    visual representations or depictions of figures, symbols, or specific images

    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
     Athenian
    -0.76
    itulo
    -0.71
     Mahomet
    -0.67
     Мексичка
    -0.66
     Athenians
    -0.66
    rawDesc
    -0.66
     Azerbai
    -0.65
     Upan
    -0.64
     Shakspeare
    -0.63
     Estelle
    -0.63
    POSITIVE LOGITS
     figure
    2.67
     figures
    2.45
    figure
    2.17
    figures
    2.14
     figured
    1.80
     FIGURES
    1.75
     figura
    1.72
     figuring
    1.55
     Figures
    1.51
     figuras
    1.44
    Activations Density 0.027%

    No Known Activations