© 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. 0-CLT-HP
    7. 95416
    Prev
    Next
    INDEX
    Explanations

    legal/code/scientific documents

    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
     HttpNotFound
    -0.57
    Autoritní
    -0.53
    invokeLater
    -0.53
     direito
    -0.52
     للمعارف
    -0.51
     appartamento
    -0.51
     Lordships
    -0.50
    #+#
    -0.50
     demografica
    -0.50
    +#+
    -0.49
    POSITIVE LOGITS
     виправивши
    0.56
    ्ड
    0.56
     License
    0.54
    //
    0.53
    oneofs
    0.53
    nze
    0.52
    ochrom
    0.52
    License
    0.51
    awtextra
    0.51
     LICENSE
    0.50
    Activations Density 1.733%

    No Known Activations