© 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. 18225
    Prev
    Next
    INDEX
    Explanations

    important phrases or statements related to titles, significant changes, and notable attributes or characteristics within text

    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
     FetchType
    -0.81
     HttpNotFound
    -0.78
     ModelExpression
    -0.74
     CreateTagHelper
    -0.73
    TagMode
    -0.73
     незавершена
    -0.73
     AssemblyTitle
    -0.68
    izoen
    -0.68
     isInitialized
    -0.66
    исленность
    -0.66
    POSITIVE LOGITS
    UnknownFields
    0.57
    Одно
    0.56
    lese
    0.49
    ESE
    0.45
    ActionMode
    0.44
    брь
    0.43
    قب
    0.42
    ON
    0.42
     pinch
    0.41
     tanda
    0.41
    Activations Density 0.689%

    No Known Activations