© 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. 0-CLT-HP
    7. 94746
    Prev
    Next
    INDEX
    Explanations

    dehydrogenase

    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
     shepherds
    -1.47
     shepherd
    -0.59
    klju
    -0.46
     /.
    -0.43
    BLES
    -0.42
     dehydrogenase
    -0.41
    rola
    -0.40
     boy
    -0.39
    maker
    -0.38
     scalable
    -0.37
    POSITIVE LOGITS
    MigrationBuilder
    0.85
     وتسجيلات
    0.84
    ValueStyle
    0.77
    зулта
    0.74
     للاسماء
    0.74
    rungsseite
    0.73
     médicale
    0.73
    Tikang
    0.70
     chinoise
    0.69
     ennemis
    0.69
    Activations Density 0.653%

    No Known Activations