© 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. 5-CLT-HP
    7. 5005
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
    CopyWith
    -0.55
    Hentet
    -0.52
    Referencie
    -0.50
    nesc
    -0.48
    СТИ
    -0.48
    nose
    -0.46
    ret
    -0.46
    BASEPATH
    -0.45
    ingo
    -0.45
    heim
    -0.45
    POSITIVE LOGITS
     ویکی‌پدیا
    0.73
    AnimationsModule
    0.66
     localObject
    0.59
    BagLayout
    0.57
    setViewportView
    0.57
     igjen
    0.56
     متعلقه
    0.56
     financière
    0.55
    bentar
    0.54
     démocr
    0.54
    Activations Density 0.001%

    No Known Activations