© 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. 38330
    Prev
    Next
    INDEX
    Explanations

    uis

    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
    une
    -0.89
    uis
    -0.66
    gan
    -0.57
    le
    -0.52
    of
    -0.52
    date
    -0.51
    go
    -0.50
     cor
    -0.49
    ys
    -0.48
    igo
    -0.47
    POSITIVE LOGITS
     nahilalakip
    1.13
     myſelf
    0.97
     насељу
    0.94
    ſelf
    0.94
     initComponents
    0.93
     itſelf
    0.92
     Majefty
    0.90
     poffible
    0.90
     ―――――
    0.85
    GEBURTSDATUM
    0.85
    Activations Density 1.046%

    No Known Activations