© 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. 24-RES-MATRYOSHKA-DC
    7. 1441
    Prev
    Next
    INDEX
    Explanations

    code related to AWS IAM policies for Kinesis and Firehose data streams

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    othek
    -0.65
    omla
    -0.58
    BASEPATH
    -0.57
    twimg
    -0.57
     messengers
    -0.57
     socket
    -0.55
    didSet
    -0.54
     Cok
    -0.54
    WebMethod
    -0.53
    atelle
    -0.53
    POSITIVE LOGITS
     Amazon
    0.77
     IAM
    0.68
    Amazon
    0.66
     AWS
    0.64
     aws
    0.63
    IAM
    0.60
     arn
    0.59
     ARN
    0.59
    arn
    0.59
    iam
    0.59
    Activations Density 0.708%

    No Known Activations