© 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. 0-CLT-HP
    4. 90709
    Prev
    Next
    INDEX
    Explanations

    Unusual vocabulary

    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
     repeating
    -0.76
     repeated
    -0.75
    Repeat
    -0.75
    repeat
    -0.72
     repetir
    -0.69
    ArgsConstructor
    -0.66
    harapkan
    -0.65
    WithMany
    -0.64
     Repeat
    -0.62
     ordenado
    -0.62
    POSITIVE LOGITS
     kasarigan
    0.53
    __.
    0.47
    tonsoft
    0.46
    ental
    0.45
     marine
    0.45
    HandlerContext
    0.44
     juice
    0.44
    aarrggbb
    0.44
     Marine
    0.43
    unately
    0.43
    Activations Density 0.085%

    No Known Activations