© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8696
    Prev
    Next
    INDEX
    Explanations

    seal

    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
    Negative Logits
     seal
    -1.42
     Seal
    -1.35
    Seal
    -1.25
    seal
    -1.22
     SEAL
    -1.20
     sealing
    -1.19
     seals
    -1.15
     Sealing
    -1.12
    SEAL
    -1.11
     Seals
    -1.06
    POSITIVE LOGITS
     للاسماء
    0.62
    MLLoader
    0.61
     Slater
    0.58
     незавершена
    0.51
    hander
    0.50
    hept
    0.50
    قلاب
    0.50
     complexity
    0.48
    odzi
    0.47
    ordes
    0.47
    Activations Density 0.093%

    No Known Activations