© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4192
    Prev
    Next
    INDEX
    Explanations

    Technical documentation

    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
     ostavi
    -0.58
    potranspiration
    -0.57
    žin
    -0.57
     intStringLen
    -0.56
    EndContext
    -0.56
     resourceCulture
    -0.54
     ddelweddau
    -0.54
     AppCompatTheme
    -0.52
    vacy
    -0.52
     opérateur
    -0.52
    POSITIVE LOGITS
    
    0.67
    THISDAY
    0.54
     chi̍t
    0.50
    +:+
    0.49
    bootstrapcdn
    0.47
    InputBorder
    0.47
     sickness
    0.46
    enumii
    0.46
    GraphicsUnit
    0.42
    
    0.42
    Activations Density 0.001%

    No Known Activations