© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5094
    Prev
    Next
    INDEX
    Explanations

    mathematical constants and symbols, particularly related to π (pi)

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protoimpl
    -0.68
     tarifs
    -0.64
     Jennings
    -0.62
     skrzy
    -0.61
     KENN
    -0.60
     censi
    -0.60
    Carolyn
    -0.59
     personne
    -0.58
     Kennedy
    -0.58
     Gass
    -0.58
    POSITIVE LOGITS
    pi
    1.35
    π
    1.27
     pi
    1.23
     π
    1.20
     PI
    1.00
    PI
    0.97
    clyde
    0.91
    pyx
    0.89
    PyObject
    0.88
    __(/*!
    0.85
    Activations Density 0.092%

    No Known Activations