© 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. 26543
    Prev
    Next
    INDEX
    Explanations

    blocks of code or programming snippets

    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
     Lohan
    -0.76
    судар
    -0.73
    WriteLiteral
    -0.70
    </em>
    -0.67
    rungsseite
    -0.66
    osgi
    -0.61
     pochod
    -0.60
    diğim
    -0.58
    orianCalendar
    -0.58
     Nadal
    -0.57
    POSITIVE LOGITS
    ```
    1.65
     ```
    1.27
    +```
    1.25
    -```
    1.14
    ?''
    0.93
    ```
    0.86
    ijão
    0.85
     \]
    0.76
     ✭✭
    0.75
    prefetch
    0.75
    Activations Density 0.002%

    No Known Activations