© 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. 631
    Prev
    Next
    INDEX
    Explanations

    Superlative adjectives

    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
    hearsed
    -0.54
    DeleteBehavior
    -0.51
    my
    -0.50
     my
    -0.49
    #+#
    -0.49
    GHIJKLM
    -0.48
    umpul
    -0.47
    romat
    -0.46
     darin
    -0.44
    chymal
    -0.44
    POSITIVE LOGITS
     Normdatei
    0.76
    AddHtmlAttribute
    0.64
    fromnode
    0.61
    XmlAccessorType
    0.58
     Vikipedi
    0.58
     mergeFrom
    0.55
    expandindo
    0.55
    Referências
    0.55
    évaluateur
    0.54
    ApiModel
    0.54
    Activations Density 0.003%

    No Known Activations