© 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. 18277
    Prev
    Next
    INDEX
    Explanations

    expressions of admiration or being impressed

    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
    味
    -0.54
     Cost
    -0.52
     joy
    -0.52
    ائع
    -0.52
     Portal
    -0.51
     Hildebrand
    -0.50
     Best
    -0.49
     gioia
    -0.49
     zada
    -0.49
    ción
    -0.49
    POSITIVE LOGITS
    Impressive
    1.19
     Impressive
    1.08
     impress
    1.05
    ########.
    1.05
     impressed
    1.00
    +#+
    0.96
     admiration
    0.94
     impressive
    0.91
     admire
    0.89
     تانيه
    0.87
    Activations Density 0.039%

    No Known Activations