© 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. 10666
    Prev
    Next
    INDEX
    Explanations

    values related to color and graphical attributes

    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
     שוליים
    -0.83
    esterday
    -0.75
     disambiguazione
    -0.74
    styleable
    -0.69
    存于互联网档案馆
    -0.66
     חיצוניים
    -0.65
    SpringBootTest
    -0.64
    ]};
    -0.63
    matchCondition
    -0.60
    DotNetBar
    -0.60
    POSITIVE LOGITS
     pinulongan
    0.49
     Blackwood
    0.47
    DockStyle
    0.47
     cá
    0.46
    Становништво
    0.43
    transQ
    0.42
    poel
    0.42
    はじめに
    0.42
    sigkeit
    0.42
     Abolition
    0.41
    Activations Density 0.003%

    No Known Activations