© 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. 242
    Prev
    Next
    INDEX
    Explanations

    the word "relationship" and related terms like "parallels"

    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
    GraphicsUnit
    -0.78
     تضيفلها
    -0.77
    ambique
    -0.59
    eterangan
    -0.56
     balsam
    -0.54
    XMLSchema
    -0.53
    janya
    -0.52
    rceil
    -0.52
    razor
    -0.52
    viewDidLoad
    -0.52
    POSITIVE LOGITS
     between
    0.98
     links
    0.96
     link
    0.93
     connections
    0.91
     Link
    0.90
     linking
    0.86
     между
    0.84
     ties
    0.84
     connection
    0.83
     LINK
    0.83
    Activations Density 1.395%

    No Known Activations