© 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. 740
    Prev
    Next
    INDEX
    Explanations

    the mathematical constant pi

    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
     protoimpl
    -0.65
    autorest
    -0.57
     ALPHA
    -0.55
    unhofer
    -0.55
     Alpha
    -0.54
     noDo
    -0.54
     alpha
    -0.53
    ALPHA
    -0.53
    تقاوى
    -0.53
    alpha
    -0.52
    POSITIVE LOGITS
    pi
    3.80
     pi
    3.09
     Pi
    2.56
    PI
    2.55
    π
    2.55
    Pi
    2.52
     π
    2.23
     PI
    2.20
    𝜋
    1.73
    
    1.66
    Activations Density 0.308%

    No Known Activations