© 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. 4-CLT-HP
    7. 2284
    Prev
    Next
    INDEX
    Explanations

    pronouns and legal context

    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
     beginnetje
    -0.79
     kasarigan
    -0.74
     udaler
    -0.70
    UnsafeEnabled
    -0.69
     purpoſe
    -0.66
     himſelf
    -0.65
     ſta
    -0.65
    enerys
    -0.64
     مشين
    -0.62
    ільки
    -0.61
    POSITIVE LOGITS
     to
    0.74
     I
    0.73
     that
    0.66
     we
    0.60
     my
    0.57
     if
    0.49
    ⓘ
    0.46
    ,
    0.46
    jsdelivr
    0.45
    FromArgb
    0.44
    Activations Density 0.001%

    No Known Activations