© 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. 20-CLT-HP
    7. 76074
    Prev
    Next
    INDEX
    Explanations

    Code related

    np_max-act-logits · 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
    ########.
    -0.54
     ISLANDS
    -0.52
    extAlignment
    -0.50
    AutoresizingMask
    -0.50
     ✭✭
    -0.50
     islas
    -0.50
    揄
    -0.49
    *{
    -0.46
    █
    -0.45
     مرئيه
    -0.45
    POSITIVE LOGITS
     propOrder
    0.68
     ProtoMessage
    0.66
    WithIOException
    0.59
    TableField
    0.59
    unnitel
    0.59
     iprot
    0.56
     Nostra
    0.55
    RegistryLite
    0.55
    Coff
    0.54
    protoc
    0.54
    Activations Density 0.002%

    No Known Activations