© 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. 565
    Prev
    Next
    INDEX
    Explanations

    a mixture of scientific jargon, names, and seemingly random character sequences, possibly related to technical documentation or code

    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
    ness
    -1.10
     Révolution
    -0.90
    nya
    -0.80
    d
    -0.79
    n
    -0.79
     ISNI
    -0.77
     архивлан
    -0.76
     leçon
    -0.74
     casquette
    -0.72
    ship
    -0.71
    POSITIVE LOGITS
    e
    1.30
     CIE
    1.00
     SAGE
    0.98
    ADE
    0.98
    LLE
    0.98
    PIE
    0.97
    FFE
    0.97
     CME
    0.96
     Sante
    0.96
    Mane
    0.96
    Activations Density 5.193%

    No Known Activations