© 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. 5-CLT-HP
    7. 91223
    Prev
    Next
    INDEX
    Explanations

    and

    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
     have
    -0.62
     may
    -0.56
     are
    -0.56
    จะมี
    -0.55
     might
    -0.55
     HAVE
    -0.54
     tends
    -0.54
     could
    -0.54
     to
    -0.53
     that
    -0.52
    POSITIVE LOGITS
     disambiguazione
    0.85
     Evaluating
    0.73
     Managing
    0.73
     Monitoring
    0.73
     Reviewing
    0.72
     Reporting
    0.71
     Correction
    0.71
     Selection
    0.69
     Recording
    0.69
     Determining
    0.68
    Activations Density 0.001%

    No Known Activations