© 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. 1-RES-MATRYOSHKA-DC
    7. 143
    Prev
    Next
    INDEX
    Explanations

    modal auxiliary verbs indicating obligation or necessity

    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
     bit
    -0.56
     been
    -0.56
     %>
    -0.56
    LikeLike
    -0.53
    irvana
    -0.52
     mene
    -0.51
    Been
    -0.50
     ways
    -0.50
    erba
    -0.49
     abit
    -0.48
    POSITIVE LOGITS
     should
    3.95
    should
    3.70
     Should
    3.69
    Should
    3.61
     SHOULD
    3.25
    hould
    2.81
     fhould
    2.55
     shouldn
    2.53
     ought
    2.39
     Shouldn
    2.30
    Activations Density 0.336%

    No Known Activations