© 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. 3642
    Prev
    Next
    INDEX
    Explanations

    the action of minimizing an error or discrepancy in an optimization context

    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
    min
    -0.63
     min
    -0.55
    Min
    -0.52
     Tags
    -0.52
     retirement
    -0.52
    mogat
    -0.51
    Tags
    -0.50
     bort
    -0.50
     Prie
    -0.50
     deregulation
    -0.50
    POSITIVE LOGITS
     minimize
    2.23
     Minim
    2.16
     minimizing
    2.14
    Minim
    2.09
    minim
    2.06
     minimise
    2.03
     minim
    2.02
     minimized
    2.02
     Minimize
    2.02
     minimization
    2.00
    Activations Density 0.031%

    No Known Activations