© 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. 95717
    Prev
    Next
    INDEX
    Explanations

    brain or body

    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
     épaules
    -0.65
     réguli
    -0.59
     tiroirs
    -0.58
    çais
    -0.55
     œufs
    -0.53
     lèvres
    -0.53
     esprits
    -0.52
     Writing
    -0.51
    يميديا
    -0.51
    nextLine
    -0.50
    POSITIVE LOGITS
     незавершена
    0.69
    sizeCache
    0.61
    ValueStyle
    0.60
     gawas
    0.59
    Rhestr
    0.58
     autorytatywna
    0.56
    tagHelperRunner
    0.55
     <=",
    0.55
    OGND
    0.54
    Välislingid
    0.53
    Activations Density 0.013%

    No Known Activations