© 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. 96620
    Prev
    Next
    INDEX
    Explanations

    ease

    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
     estimés
    -0.57
    roa
    -0.55
    HasOne
    -0.54
    Externí
    -0.52
    ])):
    -0.49
    sidemargin
    -0.49
     Willoughby
    -0.48
     زاده
    -0.47
    +#+#
    -0.47
    StoryboardSegue
    -0.47
    POSITIVE LOGITS
    ful
    0.87
    fully
    0.68
    fulness
    0.64
    WriteTagHelper
    0.61
     CreateTagHelper
    0.61
    FUL
    0.60
    ly
    0.60
    fuls
    0.59
    ZZLE
    0.57
     célé
    0.55
    Activations Density 0.002%

    No Known Activations