© 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. 31009
    Prev
    Next
    INDEX
    Explanations

    terms related to Markov chains and their properties

    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
     chức
    -0.56
    ھی
    -0.53
     zac
    -0.53
     Barn
    -0.51
    /><
    -0.50
     Münster
    -0.50
     EdgeInsets
    -0.49
    gemeinde
    -0.49
    This
    -0.48
     Melville
    -0.48
    POSITIVE LOGITS
     Markov
    1.86
    Markov
    1.70
     ExecuteAsync
    1.05
    NameInMap
    1.01
     propOrder
    0.96
    findpost
    0.95
    DeleteBehavior
    0.95
    JspWriter
    0.93
     تكبرها
    0.92
     betweenstory
    0.90
    Activations Density 0.003%

    No Known Activations