© 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. 2859
    Prev
    Next
    INDEX
    Explanations

    code and research

    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
    dija
    -0.47
    Compartir
    -0.47
    kiat
    -0.46
    xid
    -0.45
     lenker
    -0.43
     vede
    -0.43
     Кан
    -0.43
    obes
    -0.43
    nejšie
    -0.42
    adni
    -0.42
    POSITIVE LOGITS
     betweenstory
    0.68
    SBATCH
    0.65
    ſelf
    0.64
    wiſe
    0.57
     utafitiHapana
    0.57
     femininas
    0.57
     itſelf
    0.56
     ſeveral
    0.56
    neſs
    0.56
    ick
    0.56
    Activations Density 0.001%

    No Known Activations