© 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. 22-RES-MATRYOSHKA-DC
    7. 3298
    Prev
    Next
    INDEX
    Explanations

    examples of code

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     spurs
    -0.43
     Jovan
    -0.43
     fitted
    -0.43
    WriteBarrier
    -0.42
    ответ
    -0.42
     PACE
    -0.42
     Teks
    -0.41
    ptions
    -0.41
    frameCount
    -0.41
     Capit
    -0.41
    POSITIVE LOGITS
     operation
    1.20
     operations
    1.12
     Operation
    1.09
    Operation
    1.06
    operation
    1.05
     opérations
    1.02
     operate
    0.99
     Operations
    0.98
     operated
    0.96
     OPERATION
    0.96
    Activations Density 0.739%

    No Known Activations