© 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. 10331
    Prev
    Next
    INDEX
    Explanations

    the word "up" in various contexts

    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
    thâu
    -0.94
    "}"
    -0.91
     "..\..\
    -0.89
     kasarigan
    -0.89
    IUrlHelper
    -0.88
     >=",
    -0.87
    Diweddarwch
    -0.86
    ']")
    -0.84
    migrationBuilder
    -0.82
     ***!
    -0.81
    POSITIVE LOGITS
     pinggang
    0.60
    ρους
    0.59
     Bress
    0.59
     irány
    0.58
    öz
    0.56
    Unione
    0.55
    wast
    0.54
     Rag
    0.54
    ley
    0.54
    kino
    0.53
    Activations Density 0.062%

    No Known Activations