© 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. 7040
    Prev
    Next
    INDEX
    Explanations

    code snippets related to array or JSON processing

    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
     purpoſe
    -0.80
     Cæsar
    -0.78
     deſt
    -0.75
     Shakspeare
    -0.73
     uſed
    -0.72
     moschino
    -0.71
     ſtate
    -0.71
     itſelf
    -0.71
     centenary
    -0.71
     Shaksp
    -0.70
    POSITIVE LOGITS
    abestanden
    0.80
     تضيفلها
    0.68
    addContainerGap
    0.67
    )_/¯
    0.65
     spot
    0.55
     ring
    0.55
     Drink
    0.55
     kasarigan
    0.55
     Spot
    0.54
    posables
    0.50
    Activations Density 1.461%

    No Known Activations