© 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. 2978
    Prev
    Next
    INDEX
    Explanations

    references to the Mini Nutritional Assessment short form

    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
    Ljava
    -0.54
     lar
    -0.51
    침
    -0.51
     ter
    -0.50
     desper
    -0.49
     Gar
    -0.49
    jScrollPane
    -0.48
     floor
    -0.48
     ويكيميديا
    -0.48
     sol
    -0.48
    POSITIVE LOGITS
     mini
    2.94
    Mini
    2.91
     Mini
    2.88
    mini
    2.77
     MINI
    2.42
    MINI
    2.42
     miniature
    1.95
     Miniature
    1.79
    miniature
    1.72
     minis
    1.69
    Activations Density 0.006%

    No Known Activations