© 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. 1-CLT-HP
    7. 11964
    Prev
    Next
    INDEX
    Explanations

    ruby

    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
     RouterModule
    -0.54
     Element
    -0.53
    magic
    -0.53
     element
    -0.53
     propOrder
    -0.52
    geons
    -0.52
    cją
    -0.49
     فريبيس
    -0.49
    Cyfeiriadau
    -0.47
     Elements
    -0.46
    POSITIVE LOGITS
    الإنجليزية
    0.65
     femininas
    0.63
     transfieras
    0.57
     oreille
    0.56
     rédaction
    0.56
     sogget
    0.56
     spirituale
    0.56
    WhereInput
    0.55
     生命周期
    0.55
     adesivos
    0.54
    Activations Density 0.036%

    No Known Activations