© 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. 1-CLT-HP
    7. 11917
    Prev
    Next
    INDEX
    Explanations

    end

    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
    ]))
    -0.54
     SafeMath
    -0.52
    -0.50
     témoins
    -0.50
     frenos
    -0.49
     jouets
    -0.49
    Последние
    -0.49
    tagHelperRunner
    -0.49
     insectes
    -0.48
    页面存档备份
    -0.48
    POSITIVE LOGITS
    writeField
    0.56
    Stro
    0.51
     Sil
    0.51
     traffic
    0.50
    <bos>
    0.49
     locu
    0.48
    ly
    0.48
    awtextra
    0.47
    כות
    0.47
     Carri
    0.47
    Activations Density 0.214%

    No Known Activations