© 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. 1-CLT-HP
    7. 10027
    Prev
    Next
    INDEX
    Explanations

    filesystem, disk

    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
    ftagPool
    -0.59
     ویکی‌پدیا
    -0.54
    ScopeManager
    -0.48
    ᅠ
    -0.48
     estimés
    -0.46
     wikipagina
    -0.45
     smtplib
    -0.45
     Signalez
    -0.45
    httphttps
    -0.43
    SpringBootTest
    -0.43
    POSITIVE LOGITS
    Morfologia
    0.62
    ITES
    0.59
    ictwa
    0.57
    addGroup
    0.57
     Sable
    0.57
    bleau
    0.55
     Cæsar
    0.55
    êques
    0.54
     Moira
    0.54
     Gale
    0.54
    Activations Density 0.008%

    No Known Activations