© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97589
    Prev
    Next
    INDEX
    Explanations

    medical analysis

    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
     <<<<<<<<<<<<<<
    -0.68
    %)$
    -0.55
    "?>
    -0.52
     MainAxisSize
    -0.49
    prepareStatement
    -0.49
     apellidos
    -0.48
    createStatement
    -0.48
     Signalez
    -0.44
    例句
    -0.44
     okuyayım
    -0.43
    POSITIVE LOGITS
    
    0.74
     given
    0.67
     done
    0.64
     taken
    0.62
     وتسجيلات
    0.59
    casian
    0.57
     незавершена
    0.57
     flown
    0.56
    given
    0.55
    URLException
    0.53
    Activations Density 0.000%

    No Known Activations