© 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. 8673
    Prev
    Next
    INDEX
    Explanations

    Scientific/medical terminology

    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
     supérieurs
    -0.60
     at
    -0.58
     frattempo
    -0.57
     vermelha
    -0.56
     religieuses
    -0.56
     myö
    -0.56
    <bos>
    -0.56
     ویکی‌پدیا
    -0.55
     medesimo
    -0.54
    AutoField
    -0.53
    POSITIVE LOGITS
     forces
    0.49
     IMC
    0.48
     MCM
    0.48
    StateList
    0.47
    IntentFilter
    0.47
     AIA
    0.47
    SceneManagement
    0.47
     BoxFit
    0.45
    ITAN
    0.45
     ATF
    0.44
    Activations Density 0.026%

    No Known Activations