© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2451
    Prev
    Next
    INDEX
    Explanations

    intervention and cooperation

    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
     high
    -0.57
     the
    -0.52
     High
    -0.49
     its
    -0.47
     activated
    -0.47
     Union
    -0.46
     U
    -0.44
    准
    -0.44
     United
    -0.43
     Government
    -0.42
    POSITIVE LOGITS
    ValueStyle
    0.92
    ########.
    0.79
     مشين
    0.79
    tvguidetime
    0.78
    writeFieldEnd
    0.77
     Мексичка
    0.74
     متعلقه
    0.69
    +#+#
    0.68
    AddTagHelper
    0.66
    jstor
    0.66
    Activations Density 0.000%

    No Known Activations