© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 94746
    Prev
    Next
    INDEX
    Explanations

    changes, differences

    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
     "}";
    -0.56
    ecé
    -0.54
    =").
    -0.51
    ]='\
    -0.50
    '])
    
    -0.50
    +),
    -0.48
    "])
    
    -0.48
    "]);
    
    -0.47
    ]--;
    -0.47
    sqcup
    -0.47
    POSITIVE LOGITS
    IntoConstraints
    0.94
     resourceCulture
    0.77
    migrationBuilder
    0.75
    featureID
    0.74
     AssemblyVersion
    0.73
     NSCoder
    0.65
    CloseOperation
    0.65
    complexContent
    0.65
    ="@+
    0.64
    MemoryWarning
    0.63
    Activations Density 0.002%

    No Known Activations