© 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. 40972
    Prev
    Next
    INDEX
    Explanations

    firms

    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
     CreateTagHelper
    -0.74
    TagHelpers
    -0.57
    findpost
    -0.55
     Vikipedi
    -0.55
    tvguidetime
    -0.54
     firms
    -0.54
     Baillargeon
    -0.54
    bootstrapcdn
    -0.53
    IGraphics
    -0.53
     يتيمه
    -0.52
    POSITIVE LOGITS
    IVEREF
    0.57
    VELOP
    0.54
     Sper
    0.53
     quota
    0.53
    IonicModule
    0.52
    στά
    0.52
    endregion
    0.51
    cửa
    0.50
     Wiktionnaire
    0.50
    μως
    0.49
    Activations Density 0.143%

    No Known Activations