© 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. 20-CLT-HP
    7. 71800
    Prev
    Next
    INDEX
    Explanations

    patients

    np_max-act-logits · 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
     covered
    -0.59
     attacked
    -0.58
     affected
    -0.57
     Targeted
    -0.56
     Affected
    -0.56
     separated
    -0.56
     encouraged
    -0.56
     inspected
    -0.56
     impacted
    -0.56
     ruled
    -0.56
    POSITIVE LOGITS
     gotten
    0.74
    earned
    0.68
     gained
    0.67
     ComVisible
    0.64
     earned
    0.64
     ویکی‌پدیا
    0.64
     learned
    0.60
    got
    0.60
     achieved
    0.59
    StoryboardSegue
    0.59
    Activations Density 0.035%

    No Known Activations