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. 0-CLT-HP
    4. 44504
    Prev
    Next
    INDEX
    Explanations

    dii

    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
     age
    -0.59
     skipping
    -0.57
     trick
    -0.56
     alive
    -0.52
    Pil
    -0.52
     exceeding
    -0.52
     worthy
    -0.52
     tricks
    -0.50
    isFull
    -0.50
     pil
    -0.50
    POSITIVE LOGITS
     nakalista
    0.80
    WebpackPlugin
    0.66
    astify
    0.64
    +#+#
    0.63
     CURIAM
    0.60
    новниш
    0.59
    IContainer
    0.59
    });*/
    0.56
     useState
    0.56
    intellij
    0.56
    Activations Density 0.123%

    No Known Activations