© 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. 16236
    Prev
    Next
    INDEX
    Explanations

    computing and business

    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
    jure
    -0.64
    zweig
    -0.64
    etheless
    -0.63
    istically
    -0.59
    \|_{\
    -0.54
    PhysRevD
    -0.53
    JECT
    -0.52
     liquidated
    -0.51
    FFECT
    -0.50
    NEYS
    -0.48
    POSITIVE LOGITS
    ValueStyle
    0.71
     ComVisible
    0.66
    RestTemplate
    0.62
    IUrlHelper
    0.61
    richTextPanel
    0.58
    Népesség
    0.57
    Cyfeiriadau
    0.57
    EndGlobalSection
    0.57
    tagHelperRunner
    0.56
    PerformLayout
    0.56
    Activations Density 0.858%

    No Known Activations