© 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. 1-CLT-HP
    7. 9696
    Prev
    Next
    INDEX
    Explanations

    court

    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
     judge
    -0.59
    قایناق‌لار
    -0.56
     onBind
    -0.55
     DBNull
    -0.55
    南浔
    -0.55
     judges
    -0.52
    rachtet
    -0.51
    Demikian
    -0.51
     دریافت‌شده
    -0.50
    #![
    -0.50
    POSITIVE LOGITS
    PYX
    0.65
    Obrázky
    0.60
     FetchType
    0.54
    +#+#
    0.54
    <caption>
    0.50
     bpy
    0.49
     Personnel
    0.48
     يتيمه
    0.47
     MonoBehaviour
    0.47
    ronesia
    0.46
    Activations Density 0.025%

    No Known Activations