© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5574
    Prev
    Next
    INDEX
    Explanations

    is

    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
     neceff
    -0.77
     Monfieur
    -0.69
     NSCoder
    -0.69
    
    -0.68
    LookAnd
    -0.68
     neceſſ
    -0.67
     neceffary
    -0.67
    ItemBackground
    -0.66
     besoin
    -0.65
     necessity
    -0.65
    POSITIVE LOGITS
     met
    0.67
     obtained
    0.60
     there
    0.59
    met
    0.57
     present
    0.55
     achieved
    0.54
     reached
    0.54
     received
    0.52
    Met
    0.52
     Met
    0.49
    Activations Density 0.002%

    No Known Activations