© 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. 92240
    Prev
    Next
    INDEX
    Explanations

    leadership

    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
    ]=>
    -0.49
     pener
    -0.48
    principalTable
    -0.46
     Taub
    -0.45
    屎
    -0.43
    tume
    -0.43
     #(
    -0.42
    aarrggbb
    -0.42
    boxer
    -0.42
     tér
    -0.41
    POSITIVE LOGITS
    LLocation
    0.65
    WebVitals
    0.60
    EDEFAULT
    0.58
    RUnlock
    0.58
     others
    0.58
     LoggerFactory
    0.54
    forName
    0.54
    interopRequire
    0.54
     LDS
    0.54
     yourselves
    0.53
    Activations Density 0.001%

    No Known Activations