© 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. 2933
    Prev
    Next
    INDEX
    Explanations

    instances of the word "constitute" in various contexts

    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
    CompilerServices
    -1.05
     surla
    -0.96
    ⓧ
    -0.89
     MainAxisSize
    -0.88
     مرئيه
    -0.87
    oa̍t
    -0.85
    Viited
    -0.84
    dafx
    -0.79
     cherchés
    -0.78
    Vidite
    -0.77
    POSITIVE LOGITS
     constitute
    2.56
     constitutes
    2.45
     constituted
    2.44
     constituting
    1.98
     constitue
    1.68
     constituye
    1.65
     constituyen
    1.62
     constitu
    1.50
     constituer
    1.45
     costitu
    1.34
    Activations Density 0.012%

    No Known Activations