© 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. 16071
    Prev
    Next
    INDEX
    Explanations

    Pip

    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
    gate
    -0.63
    tola
    -0.61
    ftance
    -0.60
     themſelves
    -0.59
     szint
    -0.57
    territory
    -0.56
    شي
    -0.56
    RegistryLite
    -0.56
    CASA
    -0.55
    ſtance
    -0.55
    POSITIVE LOGITS
    InjectAttribute
    0.52
    GEBURTSDATUM
    0.52
    بوابة
    0.50
    MessageOf
    0.49
    ViewImports
    0.49
    Portály
    0.48
    PathVariable
    0.48
    }`);
    0.45
     فريبيس
    0.44
    Datuak
    0.44
    Activations Density 0.251%

    No Known Activations