© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 637
    Prev
    Next
    INDEX
    Explanations

    difficult

    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
    umna
    -0.48
     تانيه
    -0.48
    rentices
    -0.46
    installing
    -0.45
     installing
    -0.44
    ibilité
    -0.44
    ienes
    -0.43
    ื่อน
    -0.43
    ционных
    -0.43
    سك
    -0.43
    POSITIVE LOGITS
     to
    0.72
     ExecuteAsync
    0.68
     because
    0.66
     Wicidata
    0.65
    InSection
    0.62
    UnusedPrivate
    0.61
     picioare
    0.60
    ."));
    0.60
    ;$
    0.59
     SwitchCompat
    0.59
    Activations Density 0.002%

    No Known Activations