© 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. 5-CLT-HP
    7. 95022
    Prev
    Next
    INDEX
    Explanations

    pronouns

    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
    ември
    -0.54
     cabra
    -0.52
     Савезне
    -0.50
    IVEN
    -0.49
    於
    -0.49
    :+:
    -0.49
    uVar
    -0.48
     సౌకర్య
    -0.48
    vician
    -0.48
    fromnode
    -0.48
    POSITIVE LOGITS
    MessageTagHelper
    0.69
    TagHelper
    0.63
    IsContent
    0.59
    TagMode
    0.56
     sounded
    0.56
    aspectj
    0.55
    ModelAdmin
    0.54
     Bastion
    0.52
    ViewImports
    0.52
     bezig
    0.51
    Activations Density 0.003%

    No Known Activations