© 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. 20512
    Prev
    Next
    INDEX
    Explanations

    colons and other punctuation that indicates a separation of thoughts or lists

    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
     influence
    -0.48
    více
    -0.48
    </em>
    -0.46
    anglicky
    -0.46
    </i>
    -0.44
    PMailer
    -0.44
    வு
    -0.43
     antaranya
    -0.43
    FontStyle
    -0.43
    obra
    -0.42
    POSITIVE LOGITS
    ########.
    1.09
     виправивши
    1.03
    دانشنامهٔ
    0.98
    RegressionTest
    0.85
     kaarangay
    0.78
    webElementXpaths
    0.76
    MigrationBuilder
    0.76
    expandindo
    0.74
     Biôgrafia
    0.72
    StructEnd
    0.71
    Activations Density 0.003%

    No Known Activations