© 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. 1-CLT-HP
    7. 45585
    Prev
    Next
    INDEX
    Explanations

    description

    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
     Enterprise
    -0.89
     enterprise
    -0.87
     descriptions
    -0.86
     description
    -0.83
    Enterprise
    -0.81
    enterprise
    -0.67
     descrip
    -0.62
    description
    -0.62
    descriptions
    -0.60
    Description
    -0.57
    POSITIVE LOGITS
     lenker
    0.77
     of
    0.76
    SourceChecksum
    0.73
     MonoBehaviour
    0.70
    MemoryWarning
    0.70
    Бахар
    0.68
    __*/
    0.67
     WebDriverWait
    0.67
    发表于
    0.66
    RuleContext
    0.66
    Activations Density 0.006%

    No Known Activations