© 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. 4-CLT-HP
    4. 3148
    Prev
    Next
    INDEX
    Explanations

    of

    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
    }))
    
    -0.78
     }))
    -0.70
     })
    
    -0.67
    ."));
    -0.64
    RenderAtEndOf
    -0.62
     >=",
    -0.61
    :]:
    -0.60
    Enllaços
    -0.60
    >";
    
    -0.57
     تضيفلها
    -0.56
    POSITIVE LOGITS
     Woodrow
    0.50
    bootstrapcdn
    0.48
    usda
    0.47
     stopping
    0.46
    Scary
    0.45
     squeezing
    0.44
     Mies
    0.44
    Fixing
    0.44
    opsida
    0.44
    师傅
    0.43
    Activations Density 0.005%

    No Known Activations