© 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. 14990
    Prev
    Next
    INDEX
    Explanations

    patterns of letter combinations that relate to probability calculations

    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
     autorytatywna
    -0.74
    RenderAtEndOf
    -0.67
     <<<<<<<<<<<<<<
    -0.57
    \{\\
    -0.54
     Kode
    -0.54
    estern
    -0.53
    adaptiveStyles
    -0.52
    SharedCtor
    -0.50
     jaringan
    -0.49
    OCCURRED
    -0.49
    POSITIVE LOGITS
    hasMoreElements
    0.71
    invokeLater
    0.59
    Superview
    0.57
    istoitu
    0.57
    TemporalType
    0.55
    gnore
    0.53
     Wikispecies
    0.52
    gså
    0.50
     pastikan
    0.50
    ***************/
    0.49
    Activations Density 0.016%

    No Known Activations