© 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. 0-CLT-HP
    7. 40760
    Prev
    Next
    INDEX
    Explanations

    Names starting with "Sh"

    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
     Sh
    -1.43
    sh
    -1.30
    Sh
    -1.28
     sh
    -1.05
    SH
    -1.05
     SH
    -1.00
    shu
    -0.71
     Shu
    -0.63
    ed
    -0.53
    shm
    -0.52
    POSITIVE LOGITS
    تقاوى
    0.79
    AddTagHelper
    0.77
    tagHelperRunner
    0.76
     الحره
    0.72
    enumi
    0.71
     المعيارى
    0.71
     Eud
    0.71
     Sodom
    0.70
    ftagPool
    0.70
    PerformLayout
    0.69
    Activations Density 0.046%

    No Known Activations