© 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. 65
    Prev
    Next
    INDEX
    Explanations

    words that indicate relationships between things, like dependence, comparison, or being related.

    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
    :✨
    -0.87
    OrNil
    -0.77
    ]--;
    -0.75
    Diweddarwch
    -0.71
    ddots
    -0.71
     Cæsar
    -0.66
    UVWXYZ
    -0.66
     /\.
    -0.66
     OnTriggerEnter
    -0.65
    ?,?,
    -0.64
    POSITIVE LOGITS
     to
    0.73
     solely
    0.65
     thereto
    0.62
     primarily
    0.58
     with
    0.57
    於
    0.57
     às
    0.57
    于
    0.54
     upor
    0.54
     prés
    0.53
    Activations Density 3.799%

    No Known Activations