© 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. 30664
    Prev
    Next
    INDEX
    Explanations

    references to research support and funding sources

    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
     des
    -0.47
     <=",
    -0.45
    .
    -0.44
    ,
    -0.44
    msgTypes
    -0.44
     Vol
    -0.44
     -
    -0.42
     (
    -0.42
     desa
    -0.40
     |
    -0.40
    POSITIVE LOGITS
    Personendaten
    1.00
     }}$}
    0.84
    ']],
    0.79
    "]];
    0.76
    ]$}
    0.74
     }}"></
    0.74
    IUrlHelper
    0.72
    "]
    0.72
     pageContext
    0.72
    "]]
    0.68
    Activations Density 0.021%

    No Known Activations