© 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. 486
    Prev
    Next
    INDEX
    Explanations

    discussion/questions

    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
    ")));
    
    -0.80
    '));
    
    -0.71
    )");
    
    -0.71
    '},
    
    -0.71
     Савезне
    -0.68
     سكانية
    -0.68
    }))
    
    -0.65
    $
    
    -0.64
    RegressionTest
    -0.64
    ")){
    
    -0.63
    POSITIVE LOGITS
    cheiben
    0.53
    ;++
    0.51
     sufficient
    0.48
     BorderRadius
    0.46
    ersdorf
    0.45
    getStatusCode
    0.45
    isNameExpr
    0.43
    INOIS
    0.43
    oides
    0.42
    nance
    0.42
    Activations Density 0.025%

    No Known Activations