© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10007
    Prev
    Next
    INDEX
    Explanations

    names

    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
     élas
    -0.65
     loisirs
    -0.65
     démocr
    -0.63
     militaires
    -0.63
     ouvertes
    -0.63
     présidenti
    -0.62
     mélanger
    -0.59
     complètes
    -0.57
     déchir
    -0.57
     lèvres
    -0.57
    POSITIVE LOGITS
    CppMethod
    0.57
    titleMargin
    0.56
    uesia
    0.47
     BrowserModule
    0.47
     Wren
    0.46
     '\\;'
    0.46
     onlyOwner
    0.45
    PerformLayout
    0.45
     Waray
    0.44
    \}^{
    0.44
    Activations Density 0.009%

    No Known Activations