© 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. 16263
    Prev
    Next
    INDEX
    Explanations

    Languages/Countries

    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
    y
    -0.48
     “
    -0.42
     đâu
    -0.38
    et
    -0.38
    Padding
    -0.38
     претен
    -0.37
    コト
    -0.37
    “
    -0.36
    EClass
    -0.35
     saiba
    -0.35
    POSITIVE LOGITS
    )_/¯
    0.80
     EconPapers
    0.77
    Datuak
    0.77
    rachtet
    0.77
     useSelector
    0.77
    ValueStyle
    0.76
    GEBURTSDATUM
    0.73
    afficheront
    0.71
    ^(@)
    0.71
     متعلقه
    0.71
    Activations Density 0.003%

    No Known Activations