© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 3160
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate inclusion or exclusion criteria in a dataset or study

    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
    ismatic
    -0.58
    +#+
    -0.54
    RegistryLite
    -0.53
     polos
    -0.51
    CardBody
    -0.51
    zzleHttp
    -0.50
    corr
    -0.50
    ForRow
    -0.49
    ghijkl
    -0.49
    المكان
    -0.48
    POSITIVE LOGITS
     included
    0.71
     ostavi
    0.70
     mukaan
    0.67
    included
    0.67
    $_['
    0.65
     transférez
    0.63
    进来
    0.62
     Included
    0.60
     INCLUDED
    0.60
     للاسماء
    0.59
    Activations Density 0.746%

    No Known Activations