© 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. 0-RES-MATRYOSHKA-DC
    7. 13301
    Prev
    Next
    INDEX
    Explanations

    references to a specific linear or proportional relationship or measure

    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
     nonlinear
    -1.66
    Nonlinear
    -1.59
     Nonlinear
    -1.55
    linear
    -1.00
    lin
    -0.98
     bilinear
    -0.76
    Lin
    -0.75
    LIN
    -0.75
     Lin
    -0.73
     linearly
    -0.69
    POSITIVE LOGITS
    findpost
    0.78
    piro
    0.77
    Shu
    0.73
    BeginContext
    0.72
     الاطلاع
    0.69
     Shu
    0.69
    ignac
    0.68
    indd
    0.67
    openConnection
    0.66
     linear
    0.65
    Activations Density 0.011%

    No Known Activations