© 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. 519
    Prev
    Next
    INDEX
    Explanations

    Code and technical documentation

    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
     tibi
    -0.64
    produzione
    -0.59
    £
    -0.59
    oje
    -0.58
    jerg
    -0.57
     disambiguazione
    -0.57
     chod
    -0.56
    Espèce
    -0.56
    nė
    -0.56
    OutputType
    -0.56
    POSITIVE LOGITS
     MainAxisSize
    0.65
    tvguidetime
    0.62
     CURIAM
    0.58
    <tfoot>
    0.53
    IsContent
    0.49
    parsedMessage
    0.48
    ArgumentParser
    0.48
    __":
    
    0.47
    SneakyThrows
    0.45
    BASELINE
    0.44
    Activations Density 0.000%

    No Known Activations