© 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. 15990
    Prev
    Next
    INDEX
    Explanations

    system

    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
     defaultstate
    -0.66
    Зноскі
    -0.65
    ystems
    -0.62
    inghouse
    -0.56
    ]--;
    -0.56
    /***/
    -0.53
    '));
    -0.53
    System
    -0.52
    '>
    -0.52
    systems
    -0.51
    POSITIVE LOGITS
    seamnă
    0.59
     Exacts
    0.56
    AndEndTag
    0.54
     réservé
    0.54
     ouvertes
    0.53
    bitField
    0.52
     opérateur
    0.50
    annica
    0.49
    SourceChecksum
    0.49
    AutoSize
    0.47
    Activations Density 0.009%

    No Known Activations