© 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. 96261
    Prev
    Next
    INDEX
    Explanations

    dash

    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
     that
    -0.51
    </strong>
    -0.48
     of
    -0.45
    :
    -0.44
    .
    -0.39
     trade
    -0.39
     contact
    -0.37
     research
    -0.36
    nuff
    -0.36
     :
    -0.36
    POSITIVE LOGITS
     فريبيس
    0.75
    SharedCtor
    0.74
    astify
    0.73
     viewDidLoad
    0.68
     ویکی‌پدیا
    0.66
    saraba
    0.66
     ICP
    0.63
    Rüyada
    0.63
     blij
    0.62
    arische
    0.62
    Activations Density 0.035%

    No Known Activations