© 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. 90942
    Prev
    Next
    INDEX
    Explanations

    exception

    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
     exception
    -1.13
     accept
    -1.06
     accepted
    -1.05
     Exception
    -1.00
     Accepted
    -0.98
     ACCEPT
    -0.96
     excepted
    -0.91
     acceptance
    -0.85
     excep
    -0.84
    exception
    -0.83
    POSITIVE LOGITS
     متعلقه
    1.05
     jScrollPane
    0.94
    InjectAttribute
    0.73
    alism
    0.73
    AndEndTag
    0.72
    resave
    0.65
    ment
    0.65
    ecore
    0.65
    AutoScaleMode
    0.64
     оригіналу
    0.63
    Activations Density 0.062%

    No Known Activations