© 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. 11675
    Prev
    Next
    INDEX
    Explanations

    detailed reference information and data structures

    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
    ViewFeatures
    -0.69
     المعيارى
    -0.61
    ondissement
    -0.59
    SourceChecksum
    -0.58
     ziren
    -0.54
    wiek
    -0.53
    parsedMessage
    -0.53
    WillAppear
    -0.52
    CPtr
    -0.52
    ordum
    -0.52
    POSITIVE LOGITS
    </thead>
    0.68
     HasFactory
    0.61
     lendemain
    0.56
    RegressionTest
    0.56
    ítése
    0.54
    晴れ
    0.54
     wsz
    0.54
    例句
    0.54
    lujah
    0.54
     douceur
    0.52
    Activations Density 0.053%

    No Known Activations