© 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. 93525
    Prev
    Next
    INDEX
    Explanations

    form

    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
    tvguidetime
    -0.65
     وتسجيلات
    -0.65
     noDo
    -0.64
    urlpatterns
    -0.64
    RenderAtEndOf
    -0.57
    SerializedName
    -0.56
    $_['
    -0.54
    
    -0.54
    VersionUID
    -0.53
     IBOutlet
    -0.53
    POSITIVE LOGITS
     MessageBoxIcon
    0.51
     weevil
    0.50
    orElseThrow
    0.50
     Arki
    0.48
     comets
    0.48
    quakes
    0.48
    zerland
    0.47
    ystis
    0.47
    KommentareTeilen
    0.46
    EventQueue
    0.46
    Activations Density 0.002%

    No Known Activations