© 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. 5838
    Prev
    Next
    INDEX
    Explanations

    government officials

    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
    RenderAtEndOf
    -0.54
     Serikat
    -0.54
     arşivlendi
    -0.54
    ets
    -0.53
    eting
    -0.50
    iramente
    -0.50
    følgelig
    -0.49
    persons
    -0.48
    hire
    -0.48
    lady
    -0.46
    POSITIVE LOGITS
    تقاوى
    0.72
    adpleegd
    0.59
    beforeAll
    0.53
     *++
    0.53
     nonUne
    0.52
    phazard
    0.51
    OGND
    0.49
    SOS
    0.48
    ByVersion
    0.48
    XmlAccessType
    0.48
    Activations Density 0.003%

    No Known Activations