© 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. 5-CLT-HP
    7. 555
    Prev
    Next
    INDEX
    Explanations

    Formal language

    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
    InputBorder
    -0.61
     (
    -0.58
     CSA
    -0.56
    AddTagHelper
    -0.52
    /*
    -0.52
     AssemblyCompany
    -0.49
     muligt
    -0.48
    ("]");
    -0.48
    mergeFrom
    -0.46
     PSC
    -0.45
    POSITIVE LOGITS
     Heroes
    0.66
     Halley
    0.66
    HED
    0.62
    kiet
    0.62
     ligiloj
    0.62
    HAP
    0.61
     Hopper
    0.60
    PHA
    0.60
    Inflater
    0.59
    HF
    0.59
    Activations Density 0.004%

    No Known Activations