© 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. 25435
    Prev
    Next
    INDEX
    Explanations

    references to custom synthesis and sequencing processes in a scientific context

    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
     defStyleAttr
    -0.70
    NewUrlParser
    -0.63
    ViewImports
    -0.63
     tartalomajánló
    -0.62
     houſe
    -0.60
     purpoſe
    -0.60
    Filmo
    -0.59
    afficheront
    -0.58
     kaynağından
    -0.58
    InitVars
    -0.58
    POSITIVE LOGITS
     costs
    0.59
     cost
    0.53
     services
    0.49
     custom
    0.49
    Costs
    0.49
    costs
    0.47
     costo
    0.46
    RunWith
    0.46
     Costs
    0.45
     chez
    0.45
    Activations Density 0.125%

    No Known Activations