© 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. 15308
    Prev
    Next
    INDEX
    Explanations

    subcategories or classifications within a hierarchical structure

    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
    Personensuche
    -1.28
     itſelf
    -1.26
     ―――――
    -1.24
     ་་
    -1.22
    ]})
    -1.19
    BibitemShut
    -1.18
     myſelf
    -1.17
     themſelves
    -1.16
    脚注の使い方
    -1.15
     doubtnut
    -1.15
    POSITIVE LOGITS
    r
    0.88
     P
    0.85
    P
    0.79
     S
    0.78
     C
    0.78
    h
    0.77
    j
    0.76
     V
    0.76
     D
    0.75
     R
    0.75
    Activations Density 0.016%

    No Known Activations