© 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. 5-CLT-HP
    7. 4511
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     бывает
    -0.63
     Wiktionnaire
    -0.62
     ddelweddau
    -0.59
     händer
    -0.57
     fometimes
    -0.57
     veces
    -0.56
     sometimes
    -0.54
     chré
    -0.53
     chrétienne
    -0.53
    RUnlock
    -0.53
    POSITIVE LOGITS
    AccessorTable
    0.70
    ThroughAttribute
    0.69
    devamını
    0.62
    StructEnd
    0.58
    χρι
    0.54
    Hozzáférés
    0.54
     /$
    0.52
    Revenir
    0.52
    Показать
    0.52
    حوالہ
    0.51
    Activations Density 0.006%

    No Known Activations