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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2614
    Prev
    Next
    INDEX
    Explanations

    scientific/technical writing

    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
    ：
    -0.53
     :
    -0.51
    $',
    -0.49
     кӀ
    -0.49
     Compilation
    -0.48
     alo
    -0.47
    '));
    -0.46
     antico
    -0.46
     compilation
    -0.45
    Erreferentziak
    -0.45
    POSITIVE LOGITS
     quæ
    0.56
    xymatrix
    0.55
    iNdEx
    0.52
    TTE
    0.52
    reportWebVitals
    0.52
    readObject
    0.51
    esistenza
    0.50
    それと
    0.50
    isome
    0.50
    CHASE
    0.50
    Activations Density 0.004%

    No Known Activations