© 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. 96527
    Prev
    Next
    INDEX
    Explanations

    scientific experiments

    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
    aarrggbb
    -0.83
    ंदीखरीदारी
    -0.83
    Autoritní
    -0.81
    VIAF
    -0.67
     AssemblyCulture
    -0.66
     AssemblyCompany
    -0.65
    SourceChecksum
    -0.63
    sizeCache
    -0.63
    Vidite
    -0.62
    ContextHolder
    -0.61
    POSITIVE LOGITS
    .
    0.53
     atyp
    0.49
     للمعارف
    0.47
     WW
    0.47
    Obrázky
    0.47
    blij
    0.46
    .​
    0.46
     οπο
    0.45
    Fprintf
    0.44
     apesar
    0.43
    Activations Density 0.009%

    No Known Activations