© 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. 15851
    Prev
    Next
    INDEX
    Explanations

    instances of the word "correct" and its variations

    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
     Epson
    -0.95
     
    -0.89
     الحره
    -0.85
     Naira
    -0.81
     SizedBox
    -0.79
     GetUser
    -0.78
     dandy
    -0.77
     SqlDbType
    -0.77
     FZ
    -0.77
    ruptedException
    -0.75
    POSITIVE LOGITS
     CORRECT
    0.79
     Correct
    0.77
    tvrt
    0.73
    ascending
    0.68
    Correct
    0.66
     correct
    0.62
    richtung
    0.61
    CORRECT
    0.59
     Cah
    0.58
     Puig
    0.58
    Activations Density 0.012%

    No Known Activations