© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1785
    Prev
    Next
    INDEX
    Explanations

    cuff

    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
     quæ
    -0.90
     déput
    -0.90
     MainAxisSize
    -0.90
    
    -0.88
    berdayakan
    -0.87
     Shakspeare
    -0.85
     larmes
    -0.85
     washes
    -0.84
     washed
    -0.81
     ainfi
    -0.81
    POSITIVE LOGITS
     C
    0.59
    ↵↵
    0.56
     er
    0.56
     them
    0.56
     E
    0.55
    ier
    0.55
     her
    0.54
     ed
    0.54
    -
    0.54
     I
    0.53
    Activations Density 0.205%

    No Known Activations