© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74629
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act-logits · 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
    BeginContext
    -0.68
    AddTagHelper
    -0.60
     Iron
    -0.60
    cule
    -0.56
     onCreateView
    -0.54
    igal
    -0.54
     Steel
    -0.54
    amh
    -0.52
    StoreMessageInfo
    -0.52
    Iron
    -0.52
    POSITIVE LOGITS
     chré
    0.49
     estekak
    0.48
    ennis
    0.48
     JPanel
    0.48
     la
    0.47
    folders
    0.47
    adaptiveStyles
    0.46
     acompanhar
    0.46
     di
    0.45
     Babu
    0.45
    Activations Density 0.004%

    No Known Activations