Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74455
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     estekak
    -0.76
    WaitGroup
    -0.71
     utafitiHapana
    -0.68
     lenker
    -0.65
    ContentAsync
    -0.62
     متعلقه
    -0.61
    exitRule
    -0.61
    openConnection
    -0.60
    XmlAccessType
    -0.60
    aronder
    -0.60
    POSITIVE LOGITS
    mati
    0.46
    Still
    0.45
    ps
    0.43
     retains
    0.42
    AGGIO
    0.41
    este
    0.40
    desk
    0.40
    PRI
    0.40
    FormTagHelper
    0.40
    ds
    0.40
    Activations Density 0.003%

    No Known Activations