© 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. 31816
    Prev
    Next
    INDEX
    Explanations

    identifying details about historical figures and their backgrounds

    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
     autorytatywna
    -0.63
    Autoritní
    -0.63
    Kontrola
    -0.62
    ganu
    -0.58
    PyExc
    -0.57
    });*/
    -0.57
    })*/
    -0.56
    teborg
    -0.55
    >';
    -0.54
    trino
    -0.54
    POSITIVE LOGITS
    oa̍t
    0.68
    Localized
    0.54
    mybatisplus
    0.52
     houſe
    0.51
     स्था
    0.50
    oredCriteria
    0.50
    ContentAsync
    0.50
    ługi
    0.49
    ollectionView
    0.49
     foncé
    0.49
    Activations Density 0.036%

    No Known Activations