© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92713
    Prev
    Next
    INDEX
    Explanations

    excuse

    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
     excuse
    -2.06
    excuse
    -1.74
     Excuse
    -1.51
    Excuse
    -1.40
     excuses
    -1.34
     pardon
    -1.06
     forgive
    -1.02
    uh
    -1.00
     Pardon
    -0.96
    Pardon
    -0.96
    POSITIVE LOGITS
    providedIn
    0.59
    </caption>
    0.55
     tắt
    0.52
    ,
    0.51
    epik
    0.51
    .
    0.50
    ery
    0.50
    s
    0.50
    nik
    0.48
    mobileqq
    0.48
    Activations Density 0.055%

    No Known Activations