© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3711
    Prev
    Next
    INDEX
    Explanations

    questions

    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
     it
    -0.53
    archs
    -0.48
     we
    -0.47
    <eos>
    -0.47
    tom
    -0.46
    ↵↵
    -0.45
    eaways
    -0.44
    телите
    -0.43
     a
    -0.43
     I
    -0.42
    POSITIVE LOGITS
     مرئيه
    0.82
     '\\;'
    0.81
     esternos
    0.74
     الدولى
    0.69
    writerow
    0.69
    IsContent
    0.68
     الحره
    0.68
    aarrggbb
    0.66
     للاسماء
    0.65
     Where
    0.65
    Activations Density 0.003%

    No Known Activations