© 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. 95310
    Prev
    Next
    INDEX
    Explanations

    Paz

    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
     Paz
    -1.90
    Paz
    -1.35
     PAZ
    -1.02
     paz
    -0.94
     Мексичка
    -0.68
     Савезне
    -0.65
     nakalista
    -0.65
     esternos
    -0.64
     betweenstory
    -0.60
    ChildScrollView
    -0.59
    POSITIVE LOGITS
    KommentareTeilen
    0.67
    ukone
    0.57
    ScopeManager
    0.55
    AutoresizingMask
    0.48
    Conditional
    0.47
    ╚
    0.47
    Hosting
    0.47
    alable
    0.47
    initComponents
    0.46
    ónio
    0.44
    Activations Density 1.529%

    No Known Activations