© 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. 90677
    Prev
    Next
    INDEX
    Explanations

    formal/archaic language

    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
     descended
    -0.91
     descends
    -0.91
     borne
    -0.85
    borne
    -0.79
     Haskell
    -0.75
     Efq
    -0.75
     descend
    -0.75
     Jefus
    -0.75
     Hiram
    -0.71
     Yerevan
    -0.71
    POSITIVE LOGITS
     виправивши
    0.64
     nahilalakip
    0.55
    ⓧ
    0.52
    солю
    0.50
     Mon
    0.48
     Bon
    0.47
    Abp
    0.47
     later
    0.47
     Bull
    0.47
    forhold
    0.47
    Activations Density 1.233%

    No Known Activations