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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 41155
    Prev
    Next
    INDEX
    Explanations

    However

    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
     entanto
    -0.88
    })));
    -0.88
    uttavia
    -0.88
    +:+
    -0.84
    anmoins
    -0.83
     }}"></
    -0.80
    ]){
    
    -0.80
    '){
    
    -0.78
    )];
    
    -0.78
    styleType
    -0.78
    POSITIVE LOGITS
    ,
    0.78
     treatment
    0.53
     
    0.51
     higher
    0.51
     tumors
    0.49
      
    0.46
     treated
    0.45
    pro
    0.45
     greater
    0.45
     various
    0.44
    Activations Density 2.120%

    No Known Activations