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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74357
    Prev
    Next
    INDEX
    Explanations

    say "image"

    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
    AndEndTag
    -0.82
    IsContent
    -0.80
     ſeveral
    -0.78
     Jefus
    -0.77
    новниш
    -0.77
     Monfieur
    -0.75
    تفصیلات
    -0.74
     myſelf
    -0.74
     uſed
    -0.74
     uſe
    -0.74
    POSITIVE LOGITS
     image
    0.58
     an
    0.52
     ph
    0.52
     images
    0.49
     app
    0.49
    像
    0.49
     mental
    0.48
    inverted
    0.47
     virtual
    0.47
     e
    0.43
    Activations Density 0.004%

    No Known Activations