© 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. 202
    Prev
    Next
    INDEX
    Explanations

    quantities and proportions

    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
     فريبيس
    -0.83
    thâu
    -0.61
     onCancelled
    -0.60
     للمعارف
    -0.60
    null
    -0.58
    出版年
    -0.56
    참고
    -0.56
    ΗΣ
    -0.55
     null
    -0.53
    Przypisy
    -0.52
    POSITIVE LOGITS
     half
    0.86
     ten
    0.79
     dozen
    0.77
     thirty
    0.77
     five
    0.75
     fifteen
    0.75
     tens
    0.75
     dizaines
    0.74
     halfway
    0.73
     hundreds
    0.73
    Activations Density 2.541%

    No Known Activations