© 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. 0-CLT-HP
    7. 988
    Prev
    Next
    INDEX
    Explanations

    approximately

    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
     approximately
    -1.30
    approximately
    -1.21
     roughly
    -1.14
    Approximately
    -1.12
    roughly
    -1.08
     aproximadamente
    -1.02
     Approximately
    -0.99
    nearly
    -0.98
     nearly
    -0.94
    Nearly
    -0.94
    POSITIVE LOGITS
    InvalidProtocol
    0.86
     resourceCulture
    0.58
    InputBorder
    0.58
     ThemeData
    0.57
     ✭✭
    0.57
    awtextra
    0.56
    /*---
    0.56
     Hamma
    0.56
    ]")]
    0.56
    ponible
    0.52
    Activations Density 0.230%

    No Known Activations