© 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. 21038
    Prev
    Next
    INDEX
    Explanations

    concessive conjunctions that indicate conditions or contrasting statements

    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
    thanes
    -0.52
    anho
    -0.48
    UTERS
    -0.44
     kul
    -0.43
     terle
    -0.42
    apart
    -0.42
    lında
    -0.41
    sequelize
    -0.40
     Tribune
    -0.40
     запла
    -0.40
    POSITIVE LOGITS
    __(/*!
    0.85
    RectangleBorder
    0.83
     kasarigan
    0.82
    /*
    0.75
     kaynağından
    0.74
    rrggbb
    0.72
    CloseOperation
    0.69
    \{\\
    0.68
     """
    0.68
     Goi
    0.67
    Activations Density 0.028%

    No Known Activations