© 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. 0-CLT-HP
    7. 40401
    Prev
    Next
    INDEX
    Explanations

    dilute

    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
     loop
    -0.80
     interface
    -0.78
    loop
    -0.69
    interface
    -0.68
     interfaz
    -0.63
    veloppe
    -0.63
     avoient
    -0.62
     archive
    -0.61
     dilute
    -0.61
    ftance
    -0.61
    POSITIVE LOGITS
     of
    0.71
    tet
    0.54
    Weblinks
    0.51
    igshid
    0.51
    stylesheet
    0.49
     مشين
    0.48
     fits
    0.47
    IE
    0.47
     elimination
    0.46
    SuppressMessage
    0.46
    Activations Density 0.216%

    No Known Activations