© 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. 5-CLT-HP
    7. 6212
    Prev
    Next
    INDEX
    Explanations

    technical or academic writing

    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
     ).
    -0.61
     gynhyrchwyd
    -0.52
     )
    -0.50
    ).
    -0.50
     ),
    -0.50
     Sonnen
    -0.48
     )
    -0.48
    ExtendWith
    -0.48
    mid
    -0.47
    )।
    -0.47
    POSITIVE LOGITS
    下载附件
    0.70
    ">//
    0.66
    MessageTagHelper
    0.65
    COUVER
    0.61
    \{\\
    0.60
    PerformLayout
    0.60
    存于互联网档案馆
    0.57
    extAlignment
    0.55
    IntoConstraints
    0.54
    Архівовано
    0.53
    Activations Density 0.015%

    No Known Activations