© 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. 2-RES-MATRYOSHKA-DC
    7. 5592
    Prev
    Next
    INDEX
    Explanations

    references to the word "over," especially when it appears multiple times or with high activation levels

    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
    Carriera
    -0.74
    CloseOperation
    -0.72
    webElement
    -0.71
    %)$
    -0.70
     natten
    -0.70
    AutoScaleMode
    -0.69
     beginnetje
    -0.68
    Портал
    -0.68
     getItemCount
    -0.68
     nahilalakip
    -0.68
    POSITIVE LOGITS
    over
    1.34
    OVER
    0.82
    overs
    0.73
    oner
    0.62
    Over
    0.60
    uver
    0.60
    back
    0.59
    ological
    0.59
    ever
    0.57
    úgó
    0.56
    Activations Density 0.016%

    No Known Activations