© 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. 17661
    Prev
    Next
    INDEX
    Explanations

    evidence from recent studies in scientific research

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.58
    )?;
    -0.56
    RSpec
    -0.54
    ToAction
    -0.53
     Olds
    -0.53
    InitStruct
    -0.51
    出版年
    -0.51
    CppCodeGen
    -0.50
    IsPostBack
    -0.50
     HttpServlet
    -0.49
    POSITIVE LOGITS
     referenties
    0.65
     оригіналу
    0.60
    plet
    0.59
    denly
    0.59
     BoxDecoration
    0.58
     لينك
    0.56
    SequentialGroup
    0.54
    新たに
    0.54
     vPvB
    0.54
     correctes
    0.52
    Activations Density 0.109%

    No Known Activations