© 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. 90889
    Prev
    Next
    INDEX
    Explanations

    interpreting/translation

    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
    a
    -0.79
    o
    -0.79
    lich
    -0.72
    er
    -0.60
    en
    -0.57
    y
    -0.57
    e
    -0.56
    i
    -0.56
    an
    -0.53
     neither
    -0.52
    POSITIVE LOGITS
    niająca
    0.64
     Lanzarote
    0.61
     Behavioural
    0.60
    вгений
    0.59
     Efq
    0.59
     Personalised
    0.58
     Madeira
    0.57
    idemia
    0.57
     mouseY
    0.57
     bottling
    0.55
    Activations Density 1.765%

    No Known Activations