© 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. 3-RES-MATRYOSHKA-DC
    7. 2830
    Prev
    Next
    INDEX
    Explanations

    words that contain a "CON" or "PIR" subsequence

    oai_token-act-pair · gemini-2.0-flash
    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
    openzeppelin
    -0.51
     متعلقه
    -0.50
    pagestyle
    -0.48
     klient
    -0.47
    Client
    -0.47
    client
    -0.47
    ===========
    -0.46
     Counts
    -0.46
    connection
    -0.45
    setModel
    -0.45
    POSITIVE LOGITS
     pinulongan
    0.88
    FormTagHelper
    0.74
    AutoresizingMask
    0.73
     resourceCulture
    0.71
     chi̍t
    0.71
     HttpNotFound
    0.70
    SequentialGroup
    0.69
    :✨
    0.68
    writeField
    0.66
    URLException
    0.66
    Activations Density 0.457%

    No Known Activations