© 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. 6103
    Prev
    Next
    INDEX
    Explanations

    that

    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
     from
    -0.60
     at
    -0.50
     really
    -0.48
     very
    -0.45
     is
    -0.44
     so
    -0.42
     us
    -0.41
    washington
    -0.41
     to
    -0.39
     personally
    -0.39
    POSITIVE LOGITS
    存于互联网档案馆
    0.83
     jScrollPane
    0.81
     Theſe
    0.74
     photolibrary
    0.71
     endregion
    0.71
     transférez
    0.69
     Thon
    0.69
    RepeatedField
    0.68
    ResumeLayout
    0.66
     GoogleFonts
    0.65
    Activations Density 0.021%

    No Known Activations