© 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. 9145
    Prev
    Next
    INDEX
    Explanations

    numeric values and mathematical operations

    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
    DockStyle
    -0.90
     Majefty
    -0.83
    ArgsConstructor
    -0.82
    InputBorder
    -0.79
    RegressionTest
    -0.79
    ValueStyle
    -0.78
    adaptiveStyles
    -0.78
     myſelf
    -0.77
     InputDecoration
    -0.75
     houſe
    -0.73
    POSITIVE LOGITS
    Composable
    0.51
    MLLoader
    0.50
     net
    0.49
    dibly
    0.48
    multicolumn
    0.47
    cinta
    0.44
    રા
    0.44
    сь
    0.43
    dymyr
    0.43
     mar
    0.42
    Activations Density 0.026%

    No Known Activations