© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1597
    Prev
    Next
    INDEX
    Explanations

    the word "interaction" and words appearing nearby it

    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
     CommonModule
    -0.66
    isContained
    -0.61
    usia
    -0.60
     defStyle
    -0.59
    Ii
    -0.57
     Heu
    -0.56
     BeautifulSoup
    -0.56
     Divers
    -0.56
    
    -0.55
     deportiva
    -0.55
    POSITIVE LOGITS
     interaction
    2.84
     interactions
    2.83
     Interaction
    2.80
     Interactions
    2.73
    Interaction
    2.64
    interaction
    2.63
     interact
    2.53
    Interactions
    2.52
    interactions
    2.50
     interacts
    2.28
    Activations Density 0.071%

    No Known Activations