© 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. 422
    Prev
    Next
    INDEX
    Explanations

    computer code/encryption

    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
    Дереккөздер
    -0.85
     MainAxisSize
    -0.81
    AnchorStyles
    -0.80
    rungsseite
    -0.75
     незавершена
    -0.72
    ⓧ
    -0.72
    
    -0.72
     kasarigan
    -0.71
     متعلقه
    -0.70
    AutoScaleMode
    -0.68
    POSITIVE LOGITS
    Gam
    0.47
    )))
    
    0.42
    Amb
    0.42
    baran
    0.42
     distribution
    0.41
    كامل
    0.41
     cry
    0.41
     climb
    0.40
    argmax
    0.40
     Gam
    0.40
    Activations Density 0.003%

    No Known Activations