© 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. 96547
    Prev
    Next
    INDEX
    Explanations

    informational articles

    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
    CodeAttribute
    -0.68
    +#+#
    -0.53
    AnchorStyles
    -0.50
    ConstraintMaker
    -0.48
     revisa
    -0.46
    Such
    -0.44
    niająca
    -0.44
     Taktlose
    -0.44
     QL
    -0.43
     nós
    -0.42
    POSITIVE LOGITS
    :✨
    0.67
    Zunanje
    0.61
    [])
    0.57
     rhestr
    0.56
     each
    0.55
     what
    0.54
     why
    0.53
    Šaltiniai
    0.53
     how
    0.52
     Arkivert
    0.52
    Activations Density 0.002%

    No Known Activations