© 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. 95715
    Prev
    Next
    INDEX
    Explanations

    Deco

    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
    bank
    -0.49
    ig
    -0.47
    cast
    -0.47
    am
    -0.47
    stand
    -0.45
    ij
    -0.45
    SharedCtor
    -0.45
    site
    -0.44
     通販
    -0.44
    fug
    -0.44
    POSITIVE LOGITS
    StoryboardSegue
    0.72
     Waray
    0.68
    UnknownFieldSet
    0.65
     Shakspeare
    0.63
    EndProject
    0.60
     pinulongan
    0.59
     ElementRef
    0.59
    routeProvider
    0.59
    HtmlAttribute
    0.58
    ItemBackground
    0.58
    Activations Density 1.589%

    No Known Activations