© 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. 18-RES-MATRYOSHKA-DC
    7. 1227
    Prev
    Next
    INDEX
    Explanations

    encoded characters and abbreviations, along with some words that end in "d"

    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.18.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.18.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
     صوتيه
    -0.73
    VersionUID
    -0.67
     Glou
    -0.66
    י
    -0.66
    ه
    -0.65
     kasarigan
    -0.64
    WebVitals
    -0.61
    RefreshLayout
    -0.61
     estekak
    -0.60
     שוליים
    -0.60
    POSITIVE LOGITS
    ded
    0.69
    ดด
    0.57
    žad
    0.55
    ding
    0.55
    roids
    0.52
    fcntl
    0.52
    dddd
    0.52
    dies
    0.51
    dition
    0.51
    ged
    0.50
    Activations Density 1.077%

    No Known Activations