© 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. 1-CLT-HP
    7. 9810
    Prev
    Next
    INDEX
    Explanations

    on

    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
     GenerationType
    -0.52
     betrek
    -0.51
     OkHttpClient
    -0.50
    forChild
    -0.48
    jning
    -0.47
    ValueStyle
    -0.47
     trouvait
    -0.47
    روابط
    -0.47
    ErrUnexpectedEOF
    -0.47
     dessutom
    -0.46
    POSITIVE LOGITS
     betweenstory
    0.59
     student
    0.58
    tvguidetime
    0.55
    SaveChangesAsync
    0.52
     &___
    0.52
    ActiveRecord
    0.50
    Rüyada
    0.50
     measures
    0.49
    횟
    0.49
    */),
    0.49
    Activations Density 0.026%

    No Known Activations