© 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. 16037
    Prev
    Next
    INDEX
    Explanations

    of

    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
    #+#
    -0.70
    
    -0.65
    libft
    -0.59
     виправивши
    -0.59
     שוליים
    -0.57
    DeleteBehavior
    -0.56
    <?
    -0.55
    Revenir
    -0.55
    ★★★★☆
    -0.54
    ViewFeatures
    -0.53
    POSITIVE LOGITS
    <bos>
    1.13
     The
    0.87
     the
    0.78
    The
    0.65
     several
    0.57
     both
    0.56
     two
    0.53
     numerous
    0.47
     Both
    0.47
     over
    0.46
    Activations Density 0.010%

    No Known Activations