© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5334
    Prev
    Next
    INDEX
    Explanations

    reagents

    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
    ReadLine
    -0.53
     QtGui
    -0.51
    INSEE
    -0.51
    printStackTrace
    -0.50
    AnchorTagHelper
    -0.49
    AutoScale
    -0.49
    ழு
    -0.48
    DataSetChanged
    -0.48
    QtWidgets
    -0.48
     Thrust
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    0.75
     незавершена
    0.63
    tagHelperRunner
    0.60
     متعلقه
    0.57
    ××
    0.56
     مرئيه
    0.56
     Administrativna
    0.55
     насељу
    0.55
     AppCompatTheme
    0.51
     colpo
    0.49
    Activations Density 0.000%

    No Known Activations