© 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. 3606
    Prev
    Next
    INDEX
    Explanations

    references to specific measurement units or durations

    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
     للاسماء
    -0.80
    fjspx
    -0.75
    lorette
    -0.62
    ьаж
    -0.60
    transQ
    -0.59
    ReusableCell
    -0.59
     periodic
    -0.59
    Хьажоргаш
    -0.59
     Regular
    -0.58
     REGULAR
    -0.58
    POSITIVE LOGITS
    ResumeLayout
    0.54
    AndEndTag
    0.51
    dial
    0.50
    geslacht
    0.48
    ちな
    0.48
    BagConstraints
    0.48
    OfMonth
    0.48
    exitRule
    0.48
     comfortably
    0.48
    новниш
    0.47
    Activations Density 0.197%

    No Known Activations