© 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. 20569
    Prev
    Next
    INDEX
    Explanations

    structured academic references or citations

    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
    \{\\
    -0.85
     myſelf
    -0.77
     itſelf
    -0.75
     raiſ
    -0.74
     themſelves
    -0.73
     poffe
    -0.72
    '):
    -0.69
     Anſ
    -0.69
    __":
    -0.69
    "):
    -0.69
    POSITIVE LOGITS
     kän
    0.55
      
    0.53
    printStackTrace
    0.51
     while
    0.48
    TabView
    0.46
        
    0.45
     sensazione
    0.44
    hadapi
    0.43
    يلات
    0.42
     möjlighet
    0.42
    Activations Density 0.142%

    No Known Activations