© 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. 1-CLT-HP
    7. 46193
    Prev
    Next
    INDEX
    Explanations

    libraries

    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
     <=",
    -0.50
     Library
    -0.48
     LIBRARIES
    -0.45
     Bibliothek
    -0.45
     library
    -0.44
    Library
    -0.44
     visst
    -0.42
    (""));
    -0.42
     Libraries
    -0.41
     encargada
    -0.41
    POSITIVE LOGITS
    RegistryLite
    0.76
    awaiter
    0.74
    脚注の使い方
    0.73
    AndEndTag
    0.71
    ConstraintMaker
    0.70
    CodedInputStream
    0.68
     CreateTagHelper
    0.66
     itſelf
    0.65
    tvguidetime
    0.65
     ModelExpression
    0.64
    Activations Density 0.011%

    No Known Activations