© 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. 12-RES-MATRYOSHKA-DC
    7. 30182
    Prev
    Next
    INDEX
    Explanations

    names, particularly names of people and specific identifiers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    Sucesor
    -0.67
     snippetHide
    -0.66
    ^(@)
    -0.65
    getSystemService
    -0.64
    IPAC
    -0.64
     DOWNVOTE
    -0.62
    ſelf
    -0.61
     بيها
    -0.61
    ſelves
    -0.59
     itſelf
    -0.59
    POSITIVE LOGITS
     ujednoznacz
    0.52
     disponibilités
    0.50
    脚注の使い方
    0.50
    ThroughAttribute
    0.47
    amoan
    0.47
    évaluateur
    0.44
     Walkover
    0.43
     onBind
    0.43
    mybatisplus
    0.43
     grie
    0.39
    Activations Density 0.448%

    No Known Activations