© 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. 90889
    Prev
    Next
    INDEX
    Explanations

    Introductions/Enumerations

    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
    XmlAccessorType
    -0.79
     AssemblyTitle
    -0.74
    rungsseite
    -0.72
    expandindo
    -0.71
     kasarigan
    -0.71
    nonatomic
    -0.71
    BeginInit
    -0.70
    `;
    -0.69
     &___
    -0.68
    itm
    -0.67
    POSITIVE LOGITS
     head
    0.52
     up
    0.51
     esternos
    0.51
     here
    0.50
     grab
    0.49
    idis
    0.46
     where
    0.44
     fold
    0.44
     though
    0.43
     watch
    0.42
    Activations Density 0.008%

    No Known Activations