© 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. 24803
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and elements related to engineering or technology

    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
     viewDidLoad
    -0.55
    Населення
    -0.49
    лтемелер
    -0.48
     ciasc
    -0.46
    الإنجليزية
    -0.46
     independientes
    -0.46
    Diweddarwch
    -0.45
     مؤرشف
    -0.45
    chieben
    -0.44
    MemoryWarning
    -0.44
    POSITIVE LOGITS
    ]));
    0.68
     resourceCulture
    0.64
    Parcelize
    0.57
    principalColumn
    0.56
    protoimpl
    0.56
    interopRequire
    0.55
    verwijspagina
    0.54
    kapan
    0.52
    "]();
    0.51
     transit
    0.50
    Activations Density 0.148%

    No Known Activations