© 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. 505
    Prev
    Next
    INDEX
    Explanations

    military

    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
    Portail
    -0.65
    httphttps
    -0.60
     فريبيس
    -0.58
    
    -0.57
    Спољашње
    -0.57
    GraphicsUnit
    -0.57
    이버
    -0.56
     MediatR
    -0.54
    المراجع
    -0.54
    CloseOperation
    -0.54
    POSITIVE LOGITS
     stadio
    0.49
    RunAsync
    0.46
    новниш
    0.45
     prom
    0.45
    </strong>
    0.43
    </h4>
    0.43
    #
    0.43
     ELEMENT
    0.42
    ]")]
    0.41
    NgModule
    0.41
    Activations Density 0.026%

    No Known Activations