© 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. 5-CLT-HP
    7. 4230
    Prev
    Next
    INDEX
    Explanations

    using

    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
     myſelf
    -0.75
     BrowserModule
    -0.73
    TypedDataSet
    -0.68
    Билгалдахарш
    -0.66
    ]--;
    -0.65
     kaarangay
    -0.63
     دیکھیے
    -0.60
    Scaler
    -0.60
     >=",
    -0.60
     ujednoznacz
    -0.59
    POSITIVE LOGITS
     MainAxisSize
    0.59
    存于互联网档案馆
    0.50
    Bronnen
    0.49
     AspNetCore
    0.49
     &
    0.46
    OfMonth
    0.43
     ExecuteAsync
    0.43
     tronco
    0.42
     createState
    0.42
    ocks
    0.42
    Activations Density 0.004%

    No Known Activations