© 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. 1-CLT-HP
    7. 13399
    Prev
    Next
    INDEX
    Explanations

    astrophysics

    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
    <bos>
    -0.85
    Derbyniad
    -0.75
    OGND
    -0.68
     Administrativna
    -0.67
    Гео
    -0.58
     ویکی‌پدیا
    -0.57
    */),
    -0.55
     ويكيپيديا
    -0.55
    testcase
    -0.53
    WithIOException
    -0.52
    POSITIVE LOGITS
    getRepository
    0.52
    isinstance
    0.50
    åde
    0.50
    mesh
    0.49
    chymal
    0.49
    künfte
    0.49
     anth
    0.48
     toArray
    0.47
     Messieurs
    0.47
    と呼ば
    0.46
    Activations Density 0.034%

    No Known Activations