© 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. 8737
    Prev
    Next
    INDEX
    Explanations

    astrophysics

    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
     tags
    -0.48
    listFiles
    -0.48
     tag
    -0.45
     tot
    -0.45
    gangs
    -0.44
     luas
    -0.44
     extends
    -0.44
     activity
    -0.44
     Barnett
    -0.43
    ing
    -0.43
    POSITIVE LOGITS
    CompilerServices
    0.72
    tvguidetime
    0.71
    CloseOperation
    0.68
     ModelExpression
    0.68
     Мексичка
    0.68
    }))
    0.65
    ✨:
    0.65
    клопе
    0.62
    Jeografia
    0.60
    ValueStyle
    0.59
    Activations Density 0.061%

    No Known Activations