© 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. 994
    Prev
    Next
    INDEX
    Explanations

    phrases that are related to legal or scientific studies/cases

    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
     öyle
    -0.49
    ่านั้น
    -0.49
    那人
    -0.49
     the
    -0.46
    那样
    -0.45
     That
    -0.44
     அத
    -0.44
     Then
    -0.44
     همان
    -0.44
     وہ
    -0.44
    POSITIVE LOGITS
     this
    2.48
    this
    2.20
     here
    1.80
     này
    1.61
     hereof
    1.57
     dieses
    1.55
     tässä
    1.49
     aquí
    1.48
    This
    1.46
     đây
    1.45
    Activations Density 2.412%

    No Known Activations