© 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. 30349
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "all" in various contexts, highlighting inclusivity or universality

    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
    setVerticalGroup
    -1.05
    webElementXpaths
    -1.02
    IndentedString
    -0.98
    хьтан
    -0.96
    ThroughAttribute
    -0.95
     propOrder
    -0.92
    MigrationBuilder
    -0.91
    AsUp
    -0.91
    ArrowToggle
    -0.88
    +#+#
    -0.88
    POSITIVE LOGITS
     what
    0.68
    毕竟
    0.64
    畢竟
    0.61
     immerhin
    0.59
     aren
    0.57
    fang
    0.57
     What
    0.56
     isn
    0.56
     vị
    0.56
     Isn
    0.56
    Activations Density 0.004%

    No Known Activations