© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13032
    Prev
    Next
    INDEX
    Explanations

    references to dashed lines indicating derivatives or derivative estimates in mathematical plots

    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
    Das
    -0.84
     das
    -0.79
     Das
    -0.75
    das
    -0.74
    bootstrapcdn
    -0.68
     DAS
    -0.64
    DAS
    -0.56
    帖最后由
    -0.56
    Демографія
    -0.54
    bosch
    -0.53
    POSITIVE LOGITS
     dashed
    2.17
    dashed
    1.30
    хьтан
    0.70
    utile
    0.61
    ItemLayout
    0.59
    WindowConstants
    0.56
    midler
    0.55
     disparu
    0.53
    tdessen
    0.52
    地说道
    0.51
    Activations Density 0.001%

    No Known Activations