© 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. 95711
    Prev
    Next
    INDEX
    Explanations

    Wikipedia

    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
    er
    -1.54
     Wikipedia
    -1.20
    Wikipedia
    -0.98
     wikipedia
    -0.95
     nurse
    -0.92
    Wiki
    -0.91
     wiki
    -0.83
     Wiki
    -0.82
     Nurse
    -0.82
     Wikiped
    -0.82
    POSITIVE LOGITS
    gangen
    0.45
     speak
    0.45
    ază
    0.45
    vnd
    0.44
     zo
    0.43
     berkata
    0.43
    Петербург
    0.43
     speaks
    0.42
    кк
    0.41
     eso
    0.41
    Activations Density 0.377%

    No Known Activations