© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2441
    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
    jdons
    -0.50
    Viitteet
    -0.45
    __':
    -0.44
     about
    -0.43
    __':
    -0.43
    __":
    -0.42
    hmä
    -0.40
     transfieras
    -0.40
     насељу
    -0.40
    pshot
    -0.40
    POSITIVE LOGITS
    iastes
    0.79
    findpost
    0.66
    webElementXpaths
    0.66
     purses
    0.65
     icmp
    0.62
     חיצוניים
    0.60
     widths
    0.60
     salads
    0.60
    ★★★★☆
    0.59
     chargés
    0.59
    Activations Density 0.009%

    No Known Activations