© 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. 5519
    Prev
    Next
    INDEX
    Explanations

    references to the word "only" indicating emphasis or exclusivity

    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
     Just
    -1.06
     just
    -1.05
    Just
    -1.00
    just
    -0.96
     JUST
    -0.94
    JUST
    -0.81
     Simply
    -0.80
    Simply
    -0.75
     Simplemente
    -0.73
     simply
    -0.72
    POSITIVE LOGITS
     createState
    0.81
    ViewFeatures
    0.71
     externi
    0.65
    LabelTagHelper
    0.64
    OGND
    0.64
    lenburg
    0.64
    styleUrls
    0.58
    genheit
    0.55
    extAlignment
    0.55
    isional
    0.54
    Activations Density 0.056%

    No Known Activations