© 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. 2468
    Prev
    Next
    INDEX
    Explanations

    comparisons/degrees

    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
    Vidi
    -0.52
     rând
    -0.49
     Reese
    -0.49
     cauſe
    -0.49
    src
    -0.48
    C
    -0.47
    liegende
    -0.46
    ,:]
    -0.45
     gött
    -0.45
    Kad
    -0.45
    POSITIVE LOGITS
     تانيه
    0.69
     saites
    0.65
     للمعارف
    0.65
     متعلقه
    0.63
    rawDesc
    0.61
     상세
    0.60
    InjectAttribute
    0.60
    istoitu
    0.59
     disambiguazione
    0.59
    EndGlobalSection
    0.59
    Activations Density 0.001%

    No Known Activations