© 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. 38520
    Prev
    Next
    INDEX
    Explanations

    Thrill

    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
     Theories
    -0.74
    }}^{(
    -0.62
     wording
    -0.62
     sensation
    -0.60
     theories
    -0.58
     orbs
    -0.58
     thrill
    -0.57
    AutoScale
    -0.56
    MemoryWarning
    -0.55
     worded
    -0.54
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.63
    Aholisi
    0.63
    WriteTagHelper
    0.56
     సౌకర్య
    0.55
    Havolalar
    0.55
    ing
    0.54
     ويكيپيديا
    0.54
     кӀ
    0.53
    cito
    0.52
     مشين
    0.52
    Activations Density 0.180%

    No Known Activations