© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43262
    Prev
    Next
    INDEX
    Explanations

    {

    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
     “
    -0.52
     li
    -0.46
     site
    -0.46
     "
    -0.46
     in
    -0.44
     for
    -0.44
     The
    -0.42
     the
    -0.42
     ‘
    -0.41
    ↵↵
    -0.40
    POSITIVE LOGITS
     للمعارف
    1.13
     referenties
    1.02
    ReusableCell
    0.99
    DockStyle
    0.95
    
    0.94
    GOTREF
    0.91
     Walkover
    0.91
    sizeCache
    0.90
     незавершена
    0.88
    tvguidetime
    0.88
    Activations Density 0.087%

    No Known Activations