© 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. 5250
    Prev
    Next
    INDEX
    Explanations

    references to specific astronomical phenomena, particularly spectral features of nebulae and supernova remnants

    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
    posedge
    -0.57
    ஈ
    -0.54
    lasty
    -0.53
     caller
    -0.52
    χρι
    -0.52
    ্ড
    -0.52
     galaxy
    -0.49
    讐
    -0.49
    REW
    -0.48
     Zet
    -0.48
    POSITIVE LOGITS
    sizeCache
    0.84
    expandindo
    0.78
     <=",
    0.70
    BASELINE
    0.69
    UnusedPrivate
    0.67
    FunctionFlags
    0.60
    InjectAttribute
    0.59
     propOrder
    0.58
    -};
    0.58
    xase
    0.58
    Activations Density 0.208%

    No Known Activations