© 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. 98201
    Prev
    Next
    INDEX
    Explanations

    esophageal, medical

    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
    HtmlAttribute
    -0.62
    헌
    -0.56
    HttpPost
    -0.56
     surla
    -0.54
    httphttps
    -0.54
    ANTLR
    -0.53
    دانشنامهٔ
    -0.52
    Obrázky
    -0.50
    脚注の使い方
    -0.50
    swire
    -0.49
    POSITIVE LOGITS
     Ages
    0.59
    Age
    0.56
     Age
    0.55
    ogli
    0.54
     Paj
    0.54
    ago
    0.53
     géographique
    0.53
     konge
    0.52
    ogo
    0.52
     Gus
    0.52
    Activations Density 0.005%

    No Known Activations