© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93343
    Prev
    Next
    INDEX
    Explanations

    code/licenses

    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
     تضيفلها
    -0.78
     heapq
    -0.78
     spørs
    -0.77
     Jefus
    -0.75
    runOnUiThread
    -0.74
     FMI
    -0.73
     الحره
    -0.73
    DockStyle
    -0.73
     imprimée
    -0.73
    amaño
    -0.72
    POSITIVE LOGITS
    Tembelea
    0.64
     su
    0.57
     fin
    0.56
     th
    0.52
     
    0.51
    ⇑
    0.51
    </strong>
    0.49
     ;
    0.48
    тового
    0.48
     tr
    0.47
    Activations Density 0.007%

    No Known Activations