© 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. 10747
    Prev
    Next
    INDEX
    Explanations

    image source links

    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
     href
    -0.66
    </b>
    -0.61
     Link
    -0.51
     links
    -0.51
    </i>
    -0.51
     autorytatywna
    -0.50
    </strong>
    -0.50
     aktif
    -0.50
     link
    -0.49
     to
    -0.48
    POSITIVE LOGITS
     Monfieur
    0.94
     ſy
    0.90
     Jefus
    0.88
     Houſe
    0.84
     Diſ
    0.81
     Perſ
    0.79
     Conſ
    0.79
     ―――――
    0.78
     myſelf
    0.78
     ་་
    0.75
    Activations Density 0.003%

    No Known Activations