© 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. 8681
    Prev
    Next
    INDEX
    Explanations

    heim

    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
    heim
    -2.91
    HEIM
    -2.33
    heimer
    -1.80
     heim
    -0.93
    Heim
    -0.90
    hein
    -0.89
     Heim
    -0.82
     Himo
    -0.66
    expandindo
    -0.63
    enheim
    -0.58
    POSITIVE LOGITS
    s
    0.49
    хьтан
    0.47
    AdapterFactory
    0.45
     multiplic
    0.45
    steak
    0.44
     Wherefore
    0.44
    sho
    0.44
    WireFormat
    0.43
     slippage
    0.43
     Боль
    0.43
    Activations Density 0.023%

    No Known Activations