© 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. 97516
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     MainAxisSize
    -0.83
    TagHelper
    -0.75
    MemoryWarning
    -0.73
    AllAfrica
    -0.72
    brainly
    -0.72
    InputBorder
    -0.70
    [::-
    -0.70
    ✨:
    -0.69
     مشين
    -0.69
    ignty
    -0.69
    POSITIVE LOGITS
    ⓘ
    0.46
     suicidio
    0.44
     almuerzo
    0.43
     تحقق
    0.43
    gar
    0.42
    Ru
    0.41
    Di
    0.41
    D
    0.41
     surla
    0.41
    ◀
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.