© 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. 3-RES-MATRYOSHKA-DC
    7. 2628
    Prev
    Next
    INDEX
    Explanations

    the word "hardly" and words that sometimes follow it, especially the articles "a" or "an"

    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
     része
    -0.73
    terscotch
    -0.69
     foramen
    -0.68
    ILON
    -0.68
    msgSender
    -0.67
    idemia
    -0.67
     revanche
    -0.66
     hyö
    -0.62
     Также
    -0.60
     Philist
    -0.60
    POSITIVE LOGITS
     hardly
    2.36
     Hardly
    2.13
     barely
    1.91
     scarcely
    1.88
     едва
    1.06
     kaum
    1.03
     rarely
    0.97
     seldom
    0.89
     Rarely
    0.85
     barley
    0.84
    Activations Density 0.033%

    No Known Activations