© 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. 1-CLT-HP
    7. 8945
    Prev
    Next
    INDEX
    Explanations

    location and distribution

    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
    ViewFeatures
    -0.74
    MessageTagHelper
    -0.59
     CHtml
    -0.52
    exitRule
    -0.51
     يتيمه
    -0.50
    PMI
    -0.50
     indruk
    -0.47
     Filipino
    -0.47
    下一篇
    -0.47
    TagHelpers
    -0.46
    POSITIVE LOGITS
    MemoryWarning
    0.54
     Layers
    0.53
     layers
    0.52
    rrggbb
    0.52
    odeficiency
    0.51
     accuracy
    0.49
     Democracy
    0.49
    atric
    0.49
    Geplaatst
    0.48
     FontWeight
    0.48
    Activations Density 0.019%

    No Known Activations