© 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. 3-RES-MATRYOSHKA-DC
    7. 1616
    Prev
    Next
    INDEX
    Explanations

    instances of the prefix "poly" followed by other letters

    oai_token-act-pair · gemini-2.0-flash
    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
     Phry
    -0.88
     Hutton
    -0.84
     Justo
    -0.79
     Comstock
    -0.76
     Huguen
    -0.75
     Voit
    -0.74
     Wayback
    -0.72
     Boyer
    -0.72
    nbt
    -0.71
     Prato
    -0.70
    POSITIVE LOGITS
    poly
    1.83
     poly
    1.82
     poli
    1.73
     Poly
    1.72
    Poly
    1.70
     POL
    1.66
     POLY
    1.59
    pol
    1.56
    POLY
    1.52
    POL
    1.52
    Activations Density 1.746%

    No Known Activations