© 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. 0-CLT-HP
    7. 94102
    Prev
    Next
    INDEX
    Explanations

    system

    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
    system
    -0.58
     system
    -0.54
    ystem
    -0.53
    System
    -0.51
     System
    -0.50
    SYSTEM
    -0.50
     systems
    -0.50
     CreateTagHelper
    -0.50
     Systeme
    -0.50
    systems
    -0.49
    POSITIVE LOGITS
     contextLoads
    0.70
    cửa
    0.66
    stdc
    0.65
     drauf
    0.65
    OpenHelper
    0.64
    /*
    0.64
    pośred
    0.62
     doubtnut
    0.62
     Efq
    0.62
     Reſ
    0.61
    Activations Density 0.269%

    No Known Activations