© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 27215
    Prev
    Next
    INDEX
    Explanations

    phrases indicating proximity or immediate positioning concerning people or objects

    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
    Negative Logits
    UserScript
    -0.84
    })`
    -0.82
    VIAF
    -0.79
    StoreMessageInfo
    -0.79
     betrek
    -0.77
    RTLR
    -0.77
    StoryboardSegue
    -0.75
    cursions
    -0.74
     Joc
    -0.73
    ñora
    -0.72
    POSITIVE LOGITS
     StatefulWidget
    0.68
     أمام
    0.63
    iomanip
    0.57
    stellung
    0.55
    赫
    0.55
    面前
    0.54
     Bowie
    0.53
     kor
    0.52
     face
    0.51
    INE
    0.50
    Activations Density 0.047%

    No Known Activations