© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13425
    Prev
    Next
    INDEX
    Explanations

    feces

    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
    MemoryWarning
    -0.68
    stateProvider
    -0.62
    twimg
    -0.62
     endregion
    -0.61
    fficio
    -0.61
    MarshalTo
    -0.60
    mybatisplus
    -0.56
    ibatis
    -0.52
     variés
    -0.52
    urig
    -0.51
    POSITIVE LOGITS
    AddTagHelper
    0.59
    +#+#
    0.59
     production
    0.52
    el
    0.51
    sl
    0.50
    lined
    0.50
    liners
    0.50
    anus
    0.50
    Clik
    0.49
    elin
    0.49
    Activations Density 0.004%

    No Known Activations