© 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. 4006
    Prev
    Next
    INDEX
    Explanations

    movement or process

    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
     kasarigan
    -0.62
     automatiques
    -0.60
     élevés
    -0.60
     électroniques
    -0.60
     rapides
    -0.58
    ंदीखरीदारी
    -0.58
     récentes
    -0.57
    :✨
    -0.57
     juridiques
    -0.56
     atque
    -0.56
    POSITIVE LOGITS
     across
    0.74
    dataclass
    0.69
    HtmlAttribute
    0.61
     carefully
    0.59
     through
    0.57
     systematically
    0.55
     ujednoznacz
    0.54
     method
    0.53
    across
    0.53
     diagonally
    0.53
    Activations Density 0.001%

    No Known Activations