© 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. 0-RES-MATRYOSHKA-DC
    7. 12416
    Prev
    Next
    INDEX
    Explanations

    references to scientific figures and their labels

    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
     labeling
    -1.02
     labeled
    -0.97
     labelled
    -0.96
     Labeling
    -0.96
     labelling
    -0.95
     labels
    -0.82
     tagged
    -0.79
    labeled
    -0.79
    expandindo
    -0.78
     tagging
    -0.73
    POSITIVE LOGITS
    persky
    0.56
    CrossRef
    0.55
     materna
    0.55
    moine
    0.51
    เอง
    0.51
    sphase
    0.51
     Deportes
    0.50
    createServer
    0.49
    ymce
    0.49
    ACLE
    0.49
    Activations Density 0.004%

    No Known Activations