© 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. 1322
    Prev
    Next
    INDEX
    Explanations

    countable, code, abstracts

    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
    countable
    -1.45
     countable
    -0.82
    antuan
    -0.59
    rillation
    -0.56
    ruled
    -0.54
    erals
    -0.53
     cl
    -0.50
    umerable
    -0.50
    tiel
    -0.50
    StoryboardSegue
    -0.50
    POSITIVE LOGITS
     Paglinawan
    0.58
     '\\;'
    0.56
    complexContent
    0.56
     onAnimation
    0.56
    lorem
    0.53
     ejus
    0.52
    量
    0.52
     distances
    0.51
    +#+
    0.51
    OnAdd
    0.50
    Activations Density 1.721%

    No Known Activations