© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92911
    Prev
    Next
    INDEX
    Explanations

    investigations and research

    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
     none
    -0.89
     the
    -0.55
     my
    -0.54
     F
    -0.52
      
    -0.52
     J
    -0.50
     Sir
    -0.49
     mit
    -0.49
     i
    -0.48
     in
    -0.48
    POSITIVE LOGITS
    Билгалдахарш
    1.04
    ."));
    1.00
    bewerken
    0.92
     itſelf
    0.90
    .")
    
    0.89
    ſelves
    0.88
     виправивши
    0.88
    ."]
    0.88
     ―――――
    0.87
     ſind
    0.85
    Activations Density 0.108%

    No Known Activations