© 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. 25399
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the absence of definitive rules or standards

    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
     GenerationType
    -0.68
     المعيارى
    -0.66
    SharedCtor
    -0.65
    "}";
    -0.64
    ].(
    -0.61
    )"),
    -0.59
    :✨
    -0.58
    AccessException
    -0.56
    StandardCharsets
    -0.56
    Herzlich
    -0.53
    POSITIVE LOGITS
    arXiv
    0.69
     Réponses
    0.56
     بيها
    0.53
     ICommand
    0.51
     pushing
    0.50
     pronti
    0.49
     shou
    0.49
     AnyObject
    0.49
    Especific
    0.47
     BorderRadius
    0.47
    Activations Density 0.107%

    No Known Activations