© 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. 18-RES-MATRYOSHKA-DC
    7. 850
    Prev
    Next
    INDEX
    Explanations

    uses of the verb "to be" in the past tense and some related words.

    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.18.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.18.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
     réalis
    -0.70
     implement
    -0.56
     make
    -0.53
     find
    -0.53
     create
    -0.52
     establish
    -0.51
     determine
    -0.48
     develop
    -0.48
     deduce
    -0.47
     veckor
    -0.47
    POSITIVE LOGITS
    
    0.91
     cherchés
    0.87
    tagHelperRunner
    0.82
     taken
    0.79
    GEBURTSDATUM
    0.78
     flown
    0.78
    IndentedString
    0.78
     analysed
    0.77
     insuffisamment
    0.77
     NSCoder
    0.77
    Activations Density 1.131%

    No Known Activations