© 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. 3873
    Prev
    Next
    INDEX
    Explanations

    scientific/technical writing

    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
     pinulongan
    -0.86
    XmlAccessType
    -0.84
    CloseOperation
    -0.79
    cote
    -0.79
     ExecuteAsync
    -0.75
    ArgsConstructor
    -0.74
     propOrder
    -0.73
    Portale
    -0.72
     समीक्षक
    -0.72
    ópez
    -0.71
    POSITIVE LOGITS
    ,
    0.41
     III
    0.39
     F
    0.38
    IUrlHelper
    0.36
    F
    0.35
    SI
    0.34
     meny
    0.34
     v
    0.33
    ↵↵
    0.33
    p
    0.33
    Activations Density 0.004%

    No Known Activations