© 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. 20634
    Prev
    Next
    INDEX
    Explanations

    references to writing or contacting an organization, specifically related to the GNU General Public License

    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
    sizeCache
    -0.57
    IContainer
    -0.51
     prior
    -0.43
    })));
    -0.42
     Prior
    -0.41
    cancelButton
    -0.41
    Géographie
    -0.41
    inon
    -0.40
    gaven
    -0.40
    Referències
    -0.39
    POSITIVE LOGITS
    enumii
    0.82
     utafitiHapana
    0.77
    InputBorder
    0.76
    تقاوى
    0.73
    cerely
    0.72
    enumi
    0.71
    $_['
    0.70
    cknow
    0.69
    Autoritní
    0.68
     Reſ
    0.67
    Activations Density 0.001%

    No Known Activations