© 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. 20-CLT-HP
    7. 73246
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    protoimpl
    -0.70
    :✨
    -0.68
    MLLoader
    -0.63
    elemField
    -0.60
    seamnă
    -0.59
    contentLoaded
    -0.59
     صوتيه
    -0.59
     يتيمه
    -0.57
    fitrión
    -0.56
     étoit
    -0.56
    POSITIVE LOGITS
     washes
    0.48
    enumii
    0.45
     washed
    0.45
    億円
    0.45
     managed
    0.45
     onResponse
    0.45
    elser
    0.44
     delay
    0.43
     slow
    0.43
     delays
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.