© 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. 95517
    Prev
    Next
    INDEX
    Explanations

    uz

    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
    regation
    -1.95
    principalColumn
    -0.72
    Demografie
    -0.72
    gonic
    -0.63
    \{\\
    -0.63
    OGND
    -0.61
    mapreduce
    -0.61
    BrowserModule
    -0.60
     ExecuteAsync
    -0.60
    دانشنامهٔ
    -0.60
    POSITIVE LOGITS
    nonatomic
    0.54
     page
    0.52
    getItems
    0.51
     collège
    0.51
    ValueStyle
    0.50
     lycée
    0.49
    fhir
    0.48
    stateProvider
    0.47
    ódó
    0.47
    smiles
    0.46
    Activations Density 1.801%

    No Known Activations