© 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. 97169
    Prev
    Next
    INDEX
    Explanations

    Individuals and numbering

    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
    expliquer
    -0.47
     utafitiHapana
    -0.47
    Fac
    -0.47
    ways
    -0.42
     först
    -0.42
     moitié
    -0.42
    tiem
    -0.41
    ToMap
    -0.40
    opis
    -0.40
    lists
    -0.40
    POSITIVE LOGITS
    abestanden
    0.69
     שוליים
    0.67
     تانيه
    0.65
     دیکھیے
    0.65
    ValueStyle
    0.65
     whoſe
    0.65
    __':
    0.64
     taką
    0.62
    protoimpl
    0.62
     Trouvez
    0.62
    Activations Density 0.076%

    No Known Activations