© 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. 97046
    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
    ]--;
    -0.65
    IUrlHelper
    -0.60
     Audiodateien
    -0.59
    횟
    -0.57
     Caballero
    -0.57
     ostavi
    -0.57
     Kran
    -0.57
     createdBy
    -0.56
     jsPsych
    -0.56
     kasarigan
    -0.56
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.56
    Anch
    0.50
    ogs
    0.48
    anch
    0.45
    UnsafeEnabled
    0.44
    InputBorder
    0.43
     garaje
    0.43
    Gen
    0.43
    Condol
    0.43
    ин
    0.42
    Activations Density 0.001%

    No Known Activations