© 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. 16141
    Prev
    Next
    INDEX
    Explanations

    LIN

    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
    PyExc
    -0.78
     noqa
    -0.58
    SizeF
    -0.56
    ništ
    -0.56
     Marquez
    -0.53
    ByVersion
    -0.52
    apunov
    -0.52
     catég
    -0.51
    rosine
    -0.51
    DBNull
    -0.48
    POSITIVE LOGITS
     GenerationType
    0.66
    reactstrap
    0.63
    ();)
    0.63
    ')['
    0.52
     sekund
    0.52
     κύ
    0.51
    ضيف
    0.51
     AppCompat
    0.51
    มาะ
    0.49
    sumoto
    0.48
    Activations Density 0.206%

    No Known Activations