© 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. 0-CLT-HP
    7. 42547
    Prev
    Next
    INDEX
    Explanations

    alter

    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
     nonatomic
    -0.99
     alter
    -0.87
    tvguidetime
    -0.71
    alter
    -0.70
     mission
    -0.68
    CrossRef
    -0.68
     Alter
    -0.62
    ChildScrollView
    -0.60
     SafeMath
    -0.60
    참고
    -0.57
    POSITIVE LOGITS
     متعلقه
    0.71
     aught
    0.62
     industriale
    0.58
    p
    0.56
     للمعارف
    0.56
     iveco
    0.55
     Hopf
    0.55
     Sardin
    0.54
     scania
    0.54
     Italians
    0.54
    Activations Density 0.814%

    No Known Activations