© 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. 23569
    Prev
    Next
    INDEX
    Explanations

    code-related elements, particularly focusing on directives and property declarations

    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
    دن
    -0.50
     Cam
    -0.50
    UnusedPrivate
    -0.49
    dataclass
    -0.47
     Tw
    -0.47
    CAM
    -0.47
     cam
    -0.46
    TagHelper
    -0.46
     mens
    -0.45
     Fred
    -0.44
    POSITIVE LOGITS
    MSK
    0.97
    出版年
    0.77
    SequentialGroup
    0.75
    futbolista
    0.75
     незавершена
    0.75
     Himo
    0.70
     تانيه
    0.69
     Estatal
    0.69
    DOCTYPE
    0.68
    ISupport
    0.67
    Activations Density 0.003%

    No Known Activations