© 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. 0-CLT-HP
    4. 43545
    Prev
    Next
    INDEX
    Explanations

    academic/technical writing

    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
     or
    -2.55
     или
    -1.87
     atau
    -1.67
     eller
    -1.66
    或
    -1.66
     oder
    -1.52
     vagy
    -1.44
     nebo
    -1.41
    หรือ
    -1.39
     hoặc
    -1.38
    POSITIVE LOGITS
     Monfieur
    1.20
     myſelf
    1.04
     ―――――
    1.01
     Efq
    1.01
     Jefus
    1.00
     houſe
    0.94
     Shakspeare
    0.94
    ſelf
    0.93
     ſeveral
    0.93
     Houſe
    0.92
    Activations Density 0.054%

    No Known Activations