© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95779
    Prev
    Next
    INDEX
    Explanations

    scientific topics, somewhat random

    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
    Negative Logits
     savor
    -0.52
    kegaard
    -0.52
     createState
    -0.48
     dent
    -0.47
    AddWithValue
    -0.45
    ammans
    -0.45
    friend
    -0.44
    sertation
    -0.43
     quince
    -0.41
    withOpacity
    -0.41
    POSITIVE LOGITS
    tingly
    0.70
    NameInMap
    0.70
    MemoryWarning
    0.67
     виправивши
    0.66
    aneous
    0.60
    ically
    0.59
    ingly
    0.59
    umented
    0.58
    kháu
    0.58
    ership
    0.57
    Activations Density 0.063%

    No Known Activations