© 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. 95758
    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
    ########.
    -1.08
    httphttps
    -0.94
     BorderRadius
    -0.93
     مشين
    -0.92
    mybatisplus
    -0.92
    fillType
    -0.84
     nakalista
    -0.84
    Personendaten
    -0.82
    ⓧ
    -0.81
    BeginInit
    -0.81
    POSITIVE LOGITS
    ,
    0.91
    .
    0.75
     and
    0.59
     to
    0.55
     or
    0.54
     for
    0.53
     at
    0.53
     en
    0.53
    ↵↵
    0.52
     so
    0.50
    Activations Density 0.884%

    No Known Activations