© 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. 90939
    Prev
    Next
    INDEX
    Explanations

    broad

    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
     broader
    -1.26
     broadened
    -1.16
     broadest
    -1.14
     broad
    -1.12
    Broad
    -1.12
    broad
    -1.09
     broadening
    -1.04
     broaden
    -0.94
     vectorielles
    -0.93
     financières
    -0.93
    POSITIVE LOGITS
     or
    0.52
     out
    0.48
    Manbalar
    0.46
    ,
    0.45
    lunda
    0.45
     St
    0.44
     human
    0.43
     amount
    0.43
     B
    0.42
     confirm
    0.42
    Activations Density 0.021%

    No Known Activations