© 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. 445
    Prev
    Next
    INDEX
    Explanations

    tables or lists that include numbers and medical terminology

    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
     nakalista
    -0.93
    ArgsConstructor
    -0.66
    出版年
    -0.65
    SuppressLint
    -0.63
    ifun
    -0.60
     nonUne
    -0.60
     illus
    -0.56
    ʺ
    -0.56
     Reap
    -0.56
    
    -0.56
    POSITIVE LOGITS
                                   
    2.38
                                  
    1.73
                                
    1.72
                              
    1.68
                            
    1.66
                                 
    1.65
                               
    1.64
                             
    1.60
                          
    1.60
                           
    1.59
    Activations Density 2.195%

    No Known Activations