© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1166
    Prev
    Next
    INDEX
    Explanations

    web links and code

    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
     Antoinette
    -1.05
    SBATCH
    -0.69
     الرياضيه
    -0.66
    parsedMessage
    -0.64
     intptr
    -0.60
    oinette
    -0.53
    ároz
    -0.51
    GeoNames
    -0.51
    createClass
    -0.51
     RSSSF
    -0.50
    POSITIVE LOGITS
    таратура
    0.57
     kaynağından
    0.48
    alous
    0.48
    optString
    0.47
     LiveData
    0.47
    WithMany
    0.46
    ungalows
    0.45
     Tua
    0.44
     éte
    0.43
    expl
    0.42
    Activations Density 0.012%

    No Known Activations