© 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. 583
    Prev
    Next
    INDEX
    Explanations

    than

    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
     they
    -0.57
    with
    -0.57
    ArgumentParser
    -0.56
    SuppressMessage
    -0.54
     oleh
    -0.53
     with
    -0.53
     nemen
    -0.53
    AndEndTag
    -0.52
     did
    -0.52
    WebVitals
    -0.52
    POSITIVE LOGITS
     to
    1.28
     να
    0.70
    <bos>
    0.65
    ]));
    
    0.63
     recognising
    0.61
    }`}>
    0.60
    ."],
    0.60
     чтобы
    0.59
     recognizing
    0.59
     realising
    0.59
    Activations Density 0.002%

    No Known Activations