© 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. 91157
    Prev
    Next
    INDEX
    Explanations

    innovation

    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
     particolari
    -0.64
     eenig
    -0.63
     zijne
    -0.58
    ftagPool
    -0.58
     nélk
    -0.56
     sólido
    -0.56
    featureID
    -0.56
     isolé
    -0.56
     ainfi
    -0.56
     resourceCulture
    -0.56
    POSITIVE LOGITS
     use
    0.75
     study
    0.75
     approach
    0.70
     project
    0.63
     work
    0.62
     report
    0.60
    Билгалдахарш
    0.59
     application
    0.59
     direction
    0.57
     proposal
    0.56
    Activations Density 0.001%

    No Known Activations