© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4871
    Prev
    Next
    INDEX
    Explanations

    pronouns

    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
    nik
    -0.53
     nor
    -0.52
    entend
    -0.49
    akaan
    -0.47
    seta
    -0.47
    故
    -0.46
    zei
    -0.45
    ner
    -0.45
    дии
    -0.44
     فا
    -0.44
    POSITIVE LOGITS
    RenderAtEndOf
    0.98
     autorytatywna
    0.92
    ьаж
    0.87
     CreateTagHelper
    0.86
    SourceChecksum
    0.86
     GenerationType
    0.84
     estekak
    0.84
    CloseOperation
    0.83
    LEncoder
    0.81
    بوابة
    0.80
    Activations Density 0.007%

    No Known Activations