© 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. 13929
    Prev
    Next
    INDEX
    Explanations

    Shadows and light coverings

    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
    Chham
    -0.61
    SharedCtor
    -0.60
    tvguidetime
    -0.60
     архивлан
    -0.59
    帖最后由
    -0.57
    rieta
    -0.57
     Catawiki
    -0.57
    perity
    -0.57
    EndGlobalSection
    -0.55
     widerrufen
    -0.55
    POSITIVE LOGITS
    ungle
    0.52
    avant
    0.52
    Avant
    0.51
    ךְ
    0.50
    ]]
    0.48
    viewDidLoad
    0.47
     Avant
    0.46
     unha
    0.46
     getLayout
    0.45
     fonder
    0.45
    Activations Density 0.048%

    No Known Activations