© 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. 93855
    Prev
    Next
    INDEX
    Explanations

    Systems

    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
    Systems
    -1.34
    systems
    -1.33
     systems
    -1.30
     Systems
    -1.27
     SYSTEMS
    -1.23
    sistem
    -1.07
    SYSTEM
    -0.97
    System
    -0.94
    system
    -0.92
     SYSTEM
    -0.86
    POSITIVE LOGITS
    #+#
    0.68
    InstanceState
    0.66
     gustó
    0.64
    ISupport
    0.59
    :+:
    0.59
     المعيارى
    0.58
     AssemblyProduct
    0.56
     insuffisamment
    0.56
     respectivamente
    0.54
     répondu
    0.54
    Activations Density 0.112%

    No Known Activations