© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 32440
    Prev
    Next
    INDEX
    Explanations

    variations of the word "replace."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    
    -0.81
     متعلقه
    -0.81
    alternative
    -0.78
     Alternative
    -0.76
     Alternate
    -0.75
    Kalb
    -0.75
     ALTERNATIVE
    -0.74
     titoli
    -0.73
    Alternatives
    -0.73
    ALTERN
    -0.73
    POSITIVE LOGITS
    ness
    0.67
     Krie
    0.61
     Cæsar
    0.61
    ViewFeatures
    0.60
     Remington
    0.60
     Doppel
    0.59
    arest
    0.59
     Rens
    0.57
     Ejec
    0.56
     Sonya
    0.56
    Activations Density 0.014%

    No Known Activations