© 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. 22280
    Prev
    Next
    INDEX
    Explanations

    URLs related to GitHub

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.77
    #+#
    -0.71
    HostException
    -0.69
     deſt
    -0.69
     Wikimedijinoj
    -0.69
    Portale
    -0.68
    Сюжет
    -0.66
    AnchorTagHelper
    -0.65
     Tetrahedron
    -0.65
     ſtand
    -0.64
    POSITIVE LOGITS
    RectangleBorder
    0.62
    osan
    0.55
     Cos
    0.54
    moc
    0.53
    ARGS
    0.53
     COMPONENTS
    0.52
    beitung
    0.52
     Salam
    0.52
     Ком
    0.51
    guém
    0.51
    Activations Density 0.003%

    No Known Activations