© 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. 32495
    Prev
    Next
    INDEX
    Explanations

    symbols indicating emphasis or significance in the text

    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
    Hozzáférés
    -0.82
     Spiro
    -0.80
     useRouter
    -0.76
     onData
    -0.72
     оригіналу
    -0.71
    SessionFactory
    -0.69
    WriteTagHelper
    -0.68
     Transporter
    -0.66
    JsonInclude
    -0.66
     nakalista
    -0.66
    POSITIVE LOGITS
    †
    1.09
     †
    0.81
    dagger
    0.76
    )");
    0.75
     ‡
    0.68
    ไตล์
    0.66
    cifix
    0.66
     $)$
    0.63
    ‡
    0.62
     ')
    0.60
    Activations Density 0.000%

    No Known Activations