© 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. 22812
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that indicate the ends of statements

    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
    存于互联网档案馆
    -0.81
     NSCoder
    -0.73
    WebServlet
    -0.71
    twimg
    -0.65
    ülés
    -0.63
    MemoryWarning
    -0.61
    prnewswire
    -0.61
    ConstraintMaker
    -0.61
    AnimationsModule
    -0.61
    ometrica
    -0.61
    POSITIVE LOGITS
     Koy
    0.57
    zusch
    0.56
    ಿಸ
    0.52
     were
    0.51
     estimés
    0.50
    niss
    0.50
     as
    0.49
    ,$_
    0.48
     оригіналу
    0.47
    هن
    0.47
    Activations Density 0.002%

    No Known Activations