© 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. 5-CLT-HP
    7. 2659
    Prev
    Next
    INDEX
    Explanations

    funded

    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
    GraphicsUnit
    -0.81
     affichés
    -0.57
    Hozzáférés
    -0.57
     defaultstate
    -0.56
    queryInterface
    -0.55
     StatefulWidget
    -0.53
    Unnamed
    -0.51
     IBOutlet
    -0.50
     Normdatei
    -0.50
     محفوظة
    -0.49
    POSITIVE LOGITS
     typelib
    0.61
    ArrowToggle
    0.60
    StoryboardSegue
    0.60
     ligiloj
    0.59
     Paglinawan
    0.59
    IUrlHelper
    0.58
    మీ
    0.54
     Signalez
    0.54
     ResourceManager
    0.53
     STC
    0.52
    Activations Density 0.000%

    No Known Activations