© 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. 1616
    Prev
    Next
    INDEX
    Explanations

    paper

    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
     snippetHide
    -1.09
    ]--;
    -0.98
    kháu
    -0.96
     Мексичка
    -0.93
    webElementXpaths
    -0.91
    parsedMessage
    -0.89
    UnusedPrivate
    -0.84
    transQ
    -0.84
    :+:
    -0.83
     EconPapers
    -0.83
    POSITIVE LOGITS
    ↵↵
    0.77
    ↵
    0.67
    .
    0.56
     from
    0.56
    <eos>
    0.53
       
    0.52
     by
    0.52
     here
    0.50
     to
    0.50
    ,
    0.49
    Activations Density 0.123%

    No Known Activations