© 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. 9395
    Prev
    Next
    INDEX
    Explanations

    strong emphasis on an empty state or initialization checks

    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
     يتيمه
    -0.51
     listos
    -0.50
     femminile
    -0.48
     '\\;'
    -0.48
    InjectAttribute
    -0.47
    kében
    -0.47
    TouchListener
    -0.47
     adulte
    -0.46
    makeConstraints
    -0.46
    SourceChecksum
    -0.45
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.80
     iParam
    0.69
     Jefus
    0.63
    RenderAtEndOf
    0.63
     pleaſure
    0.62
    ้อมูล
    0.60
    (@"%@",
    0.60
    CDCl
    0.60
     Schauspiel
    0.59
     juſ
    0.59
    Activations Density 0.002%

    No Known Activations