© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-RES-MATRYOSHKA-DC
    7. 729
    Prev
    Next
    INDEX
    Explanations

    data tables showing numbers and relationships between them

    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.24.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.24.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
    »),
    -1.16
    ),”
    -1.15
    )».
    -1.11
    »).
    -1.09
    ,»
    -1.05
    ).</
    -1.04
    ."),
    -1.02
    ).”
    -1.00
    '));
    -1.00
    ),"
    -0.98
    POSITIVE LOGITS
                                   
    2.69
           
    2.67
          
    2.63
             
    2.63
              
    2.63
               
    2.63
                   
    2.63
                       
    2.59
                 
    2.58
                  
    2.58
    Activations Density 4.231%

    No Known Activations