© 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. 3096
    Prev
    Next
    INDEX
    Explanations

    words related to "operation," "function," or "action," specifically forms of the root "ion" or "ction."

    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
     Initialized
    -0.73
    InvalidProtocol
    -0.71
    Analyzing
    -0.69
    Diwedd
    -0.63
     Analyzing
    -0.63
    umented
    -0.61
    érables
    -0.61
    atized
    -0.60
    HasForeignKey
    -0.59
    AsUp
    -0.58
    POSITIVE LOGITS
    tion
    2.08
    tions
    1.88
    ion
    1.78
    sion
    1.75
    ION
    1.70
    TION
    1.50
    ction
    1.40
    ção
    1.37
    tional
    1.36
     tion
    1.34
    Activations Density 0.175%

    No Known Activations