© 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. 1-RES-MATRYOSHKA-DC
    7. 142
    Prev
    Next
    INDEX
    Explanations

    comparisons indicating that one option surpasses another in a specified measure or attribute

    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
    kháu
    -0.69
     jScrollPane
    -0.66
     great
    -0.65
    非常的
    -0.65
    great
    -0.63
    dataflow
    -0.63
     CWE
    -0.63
    olutamente
    -0.62
    nestjs
    -0.60
    IntoConstraints
    -0.59
    POSITIVE LOGITS
     larger
    2.69
     higher
    2.67
     bigger
    2.67
     stronger
    2.59
    larger
    2.58
    higher
    2.53
     better
    2.52
     faster
    2.47
    better
    2.47
     greater
    2.45
    Activations Density 0.644%

    No Known Activations