© 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. 43158
    Prev
    Next
    INDEX
    Explanations

    enforcement

    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
     enforcement
    -1.03
     Enforcement
    -0.85
    enforcement
    -0.75
    Enforcement
    -0.74
     enforcing
    -0.70
    __':
    -0.70
     enforced
    -0.68
     /\.
    -0.62
     BIBSYS
    -0.62
     resultCode
    -0.60
    POSITIVE LOGITS
    Наде
    0.51
    webElementXpaths
    0.49
     Наде
    0.48
    достатки
    0.47
    andin
    0.46
    hood
    0.46
     ar
    0.46
    endfor
    0.46
    再见
    0.46
    탭
    0.46
    Activations Density 1.027%

    No Known Activations