© 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. 6757
    Prev
    Next
    INDEX
    Explanations

    the structure of complex mathematical expressions, particularly array or matrix structures

    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
     List
    -0.63
     pendek
    -0.57
    \}\\
    -0.56
    withOpacity
    -0.52
     list
    -0.51
     포함
    -0.50
    তথ্যসূত্র
    -0.50
     列表
    -0.49
     viens
    -0.49
    ക്ക്
    -0.48
    POSITIVE LOGITS
    array
    2.56
     array
    1.77
    arrays
    1.33
    ARRAY
    1.32
     arrays
    1.31
    Array
    1.21
     Array
    1.19
    tabular
    1.18
     ARRAY
    1.17
     Arrays
    1.02
    Activations Density 0.013%

    No Known Activations