© 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. 96629
    Prev
    Next
    INDEX
    Explanations

    comparisons/quantities

    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
     OFDb
    -0.73
     насељу
    -0.72
     سكانية
    -0.63
     createContext
    -0.61
    참고
    -0.60
    +#+#
    -0.60
    UrlResolution
    -0.60
    uffle
    -0.59
     متعلقه
    -0.59
    rscheinlich
    -0.58
    POSITIVE LOGITS
     laaj
    0.65
    DockStyle
    0.63
    ecker
    0.51
    TS
    0.47
    shank
    0.47
    Exec
    0.46
    stanti
    0.46
    are
    0.46
     whole
    0.45
    BeginInit
    0.44
    Activations Density 0.007%

    No Known Activations