© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92116
    Prev
    Next
    INDEX
    Explanations

    Scientific/medical texts

    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
     are
    -0.67
     were
    -0.51
    leyebilirsiniz
    -0.49
     have
    -0.48
     the
    -0.48
     these
    -0.48
     ARE
    -0.48
     są
    -0.47
     use
    -0.47
     their
    -0.47
    POSITIVE LOGITS
    
    0.77
    ########.
    0.71
    IntoConstraints
    0.66
     समीक्षाओं
    0.63
    urlpatterns
    0.61
     Roskov
    0.60
    IndentedString
    0.60
    Personensuche
    0.60
     BoxDecoration
    0.59
    ConstraintMaker
    0.59
    Activations Density 0.004%

    No Known Activations