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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96700
    Prev
    Next
    INDEX
    Explanations

    medical/scientific abstracts

    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
     InputDecoration
    -0.58
     Financial
    -0.57
     National
    -0.57
     Capital
    -0.56
     Blue
    -0.56
     Central
    -0.55
     Common
    -0.54
     Clean
    -0.54
     Community
    -0.53
     Market
    -0.53
    POSITIVE LOGITS
     betweenstory
    0.68
    migrationBuilder
    0.66
    دانشنامهٔ
    0.64
    NameInMap
    0.60
    /*
    0.58
     كمان
    0.56
    <bos>
    0.56
     ſee
    0.52
     purpoſe
    0.52
     كومونز
    0.51
    Activations Density 0.066%

    No Known Activations