© 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. 500
    Prev
    Next
    INDEX
    Explanations

    references to protein labels, specifically various forms of the letter "P" and "p" related to protein identifiers

    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
    Pre
    -0.55
     Patel
    -0.54
    PutMapping
    -0.54
    PATH
    -0.51
    POST
    -0.51
     PATH
    -0.50
     Potts
    -0.49
     Perkins
    -0.49
     Porter
    -0.49
     Pre
    -0.48
    POSITIVE LOGITS
    p
    2.81
     p
    2.56
    ｐ
    1.40
    𝑝
    1.36
    setP
    1.23
     P
    1.20
    P
    1.16
    getP
    1.13
    𝐩
    1.06
     getP
    1.02
    Activations Density 0.683%

    No Known Activations