© 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. 1-CLT-HP
    7. 13606
    Prev
    Next
    INDEX
    Explanations

    This

    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
     avoient
    -0.84
    ThroughAttribute
    -0.78
     étoient
    -0.78
     pintadas
    -0.76
    RTLR
    -0.74
    脚注の使い方
    -0.73
     enfans
    -0.73
     Normdatei
    -0.70
     aikaa
    -0.68
     الحره
    -0.68
    POSITIVE LOGITS
     accounts
    0.49
     Процитовано
    0.46
    marvin
    0.46
     results
    0.45
     محفوظة
    0.41
     best
    0.41
    Accounts
    0.41
     ré
    0.41
     expect
    0.40
     bruit
    0.40
    Activations Density 0.006%

    No Known Activations