© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45231
    Prev
    Next
    INDEX
    Explanations

    unusual things

    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
    PropertyGroup
    -0.62
    ôtel
    -0.57
     of
    -0.55
     rangs
    -0.54
    UpInside
    -0.51
    了什么
    -0.50
    HandlerContext
    -0.49
    ActivityCompat
    -0.48
     recommandée
    -0.47
     portée
    -0.47
    POSITIVE LOGITS
    tonode
    0.63
    yelitis
    0.63
     defaultstate
    0.59
     endwhile
    0.59
    UnsafeEnabled
    0.59
    }));
    
    0.58
     Judaism
    0.58
     Judah
    0.58
    __(/*!
    0.57
     Waray
    0.57
    Activations Density 0.096%

    No Known Activations