© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1050
    Prev
    Next
    INDEX
    Explanations

    code-related terms along with computer network error codes and consumption, along with medical terms

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.50
     Nuestro
    -0.48
    ázaro
    -0.47
    astify
    -0.47
    ienced
    -0.46
    HasAnnotation
    -0.45
    SocketChannel
    -0.45
    TTE
    -0.45
     Jok
    -0.45
     ſen
    -0.45
    POSITIVE LOGITS
           
    1.05
            
    0.69
    AndEndTag
    0.64
    
    0.63
          
    0.63
    zerne
    0.60
     defStyle
    0.60
    Personensuche
    0.60
     lingue
    0.56
             
    0.55
    Activations Density 0.455%

    No Known Activations