© 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. 4-CLT-HP
    7. 3499
    Prev
    Next
    INDEX
    Explanations

    references to text

    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
    发表于
    -0.72
    Sucesor
    -0.59
    éraires
    -0.56
     चीज़ों
    -0.56
     Psal
    -0.56
    athione
    -0.55
    endforeach
    -0.55
     blest
    -0.54
    deauna
    -0.54
    ρέπει
    -0.54
    POSITIVE LOGITS
    webElementGuid
    0.63
     and
    0.53
    InjectAttribute
    0.52
     bianche
    0.47
     gyhoeddwyd
    0.44
    MLLoader
    0.44
    Diweddarwch
    0.43
    ksp
    0.43
    CPtr
    0.42
     sentenza
    0.41
    Activations Density 0.003%

    No Known Activations