© 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. 1-CLT-HP
    4. 15106
    Prev
    Next
    INDEX
    Explanations

    code and finance

    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
     Dyer
    -1.66
    "]);
    
    -0.52
    __*/
    -0.50
    '])){
    
    -0.49
    >");
    
    -0.47
    __',
    -0.47
    '),
    
    -0.47
    ')],
    -0.47
    tichetta
    -0.47
    znej
    -0.47
    POSITIVE LOGITS
     Paglinawan
    0.64
    principalColumn
    0.62
    DebuggerStep
    0.56
    흑
    0.52
    calaureate
    0.52
     Biôgrafia
    0.52
    RegistryLite
    0.51
    posedge
    0.51
     propOrder
    0.51
     StatelessWidget
    0.50
    Activations Density 0.024%

    No Known Activations