© 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. 4-CLT-HP
    7. 3096
    Prev
    Next
    INDEX
    Explanations

    towel

    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
     للمعارف
    -0.67
    __*/
    -0.62
     nakalista
    -0.61
     ujednoznacz
    -0.59
    cstdio
    -0.56
     архивлан
    -0.54
    JspWriter
    -0.54
    Tikang
    -0.54
    CrossRef
    -0.53
    gor
    -0.51
    POSITIVE LOGITS
     réalisées
    0.52
    liesslich
    0.50
     विश्वसनीयता
    0.49
     rodríguez
    0.48
    GEBURTSDATUM
    0.47
    Websites
    0.46
     Veget
    0.46
     Provisional
    0.45
    Dob
    0.45
    ihr
    0.44
    Activations Density 0.003%

    No Known Activations