© 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. 40419
    Prev
    Next
    INDEX
    Explanations

    Legal/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
    featureID
    -1.09
    OGND
    -0.94
     Савезне
    -0.93
    Portale
    -0.86
     bezeichneter
    -0.85
     ExecuteAsync
    -0.85
    oredCriteria
    -0.84
    LEncoder
    -0.84
     NSCoder
    -0.82
    WithIOException
    -0.80
    POSITIVE LOGITS
    رائ
    0.54
    嬉
    0.49
     for
    0.49
    ↵
    0.48
    .
    0.47
    ized
    0.47
     in
    0.47
     sest
    0.47
    ize
    0.46
     best
    0.45
    Activations Density 0.039%

    No Known Activations