© 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. 3-RES-MATRYOSHKA-DC
    7. 2712
    Prev
    Next
    INDEX
    Explanations

    numerical codes or labels, often in the context of medical or legal documents

    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
    RenderAtEndOf
    -0.72
    BorderLayout
    -0.55
    Malformed
    -0.54
     endfor
    -0.54
    ərbaycan
    -0.51
     مواليد
    -0.51
     compound
    -0.50
    Explicación
    -0.50
    ňte
    -0.50
     (!_
    -0.50
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.84
    Autoritní
    0.69
    Tembelea
    0.68
    ografija
    0.56
     مرئيه
    0.53
     Италијани
    0.52
    expandindo
    0.52
    PMailer
    0.52
    fjspx
    0.52
    ftagPool
    0.50
    Activations Density 0.623%

    No Known Activations