© 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. 5-CLT-HP
    7. 2278
    Prev
    Next
    INDEX
    Explanations

    to

    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
     the
    -0.64
     fjer
    -0.53
     langt
    -0.52
     szüks
    -0.52
     Gough
    -0.52
     adsorption
    -0.52
     хватает
    -0.50
     réguli
    -0.50
     NDEBUG
    -0.49
    premi
    -0.49
    POSITIVE LOGITS
     be
    1.01
    MENAFN
    0.77
     have
    0.72
     qualify
    0.70
    期刊论文
    0.66
     feel
    0.65
    ttino
    0.62
    Datuak
    0.60
     الحره
    0.60
    MLLoader
    0.60
    Activations Density 0.001%

    No Known Activations