© 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. 0-CLT-HP
    7. 90654
    Prev
    Next
    INDEX
    Explanations

    honorifics

    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
     esternos
    -0.54
    ">>
    -0.49
     -\
    -0.48
    Clik
    -0.46
    
    -0.46
    ouncements
    -0.45
     resourceCulture
    -0.44
    PROLOG
    -0.44
    stdc
    -0.43
    ADVERTISEMENT
    -0.43
    POSITIVE LOGITS
     Theſe
    0.62
     myſelf
    0.57
    WithMany
    0.57
    ReusableCell
    0.56
     Monfieur
    0.55
    ſelf
    0.52
     JpaRepository
    0.52
    ModelAdmin
    0.52
    DockStyle
    0.51
    ſelves
    0.49
    Activations Density 0.012%

    No Known Activations