© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93748
    Prev
    Next
    INDEX
    Explanations

    Thanksgiving

    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
    expandindo
    -1.04
     Мексичка
    -0.93
     maintained
    -0.91
    httphttps
    -0.91
    WebVitals
    -0.89
     hurt
    -0.84
     Вікі
    -0.84
     سكانية
    -0.82
    verifyException
    -0.81
    脚注の使い方
    -0.81
    POSITIVE LOGITS
    ly
    0.56
    fully
    0.44
    們
    0.42
    getChildAt
    0.41
    J
    0.41
    inde
    0.40
    summary
    0.38
    dia
    0.38
     engel
    0.38
     Sochi
    0.37
    Activations Density 0.173%

    No Known Activations