© 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. 5239
    Prev
    Next
    INDEX
    Explanations

    references to the "sole" or "only" in a context

    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
     <<<<<<<<<<<<<<
    -0.68
     chiff
    -0.65
     Gifford
    -0.65
     Poitiers
    -0.65
    subsubsection
    -0.64
    новниш
    -0.62
    richTextPanel
    -0.62
    mousemove
    -0.61
     Надо
    -0.60
     Audiodateien
    -0.60
    POSITIVE LOGITS
     sole
    2.81
     Sole
    2.69
    sole
    2.59
    Sole
    2.58
     SOLE
    2.34
    SOLE
    1.92
     solely
    1.72
     soles
    1.63
     solo
    1.51
     lone
    1.40
    Activations Density 0.023%

    No Known Activations