© 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. 12-RES-MATRYOSHKA-DC
    7. 28570
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "be" in various forms

    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
    Not in Any Lists

    No Comments

    Negative Logits
     able
    -0.63
     referenties
    -0.57
    Sen
    -0.55
     SEN
    -0.54
    reactivex
    -0.54
     isInitialized
    -0.54
     ability
    -0.53
    UserScript
    -0.52
     Sen
    -0.50
    rophes
    -0.50
    POSITIVE LOGITS
     saites
    0.86
    (!__
    0.70
    esseract
    0.65
    LOYEES
    0.63
    úgó
    0.62
     Ahli
    0.61
    }}_{
    0.60
    parency
    0.60
    cellulose
    0.60
    ocide
    0.59
    Activations Density 0.026%

    No Known Activations