© 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. 30883
    Prev
    Next
    INDEX
    Explanations

    the mention of the name "Jones."

    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
     bezeichneter
    -0.85
     ]
    -0.71
    期刊论文
    -0.69
     removeAll
    -0.68
    Shelly
    -0.66
    '));
    -0.64
    =";
    -0.64
     Sheldon
    -0.64
     mannequin
    -0.64
    mij
    -0.64
    POSITIVE LOGITS
     Jones
    2.02
    Jones
    1.93
    jones
    1.73
     jones
    1.70
     JONES
    1.67
     kaynağından
    0.91
    es
    0.85
    extAlignment
    0.81
     Cyclo
    0.77
     Snowden
    0.77
    Activations Density 0.005%

    No Known Activations