© 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. 363
    Prev
    Next
    INDEX
    Explanations

    the word "be" in various forms

    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
     itſelf
    -1.40
     myſelf
    -1.33
     ſtill
    -1.30
     purpoſe
    -1.22
     alſo
    -1.18
     Majefty
    -1.17
     Jefus
    -1.17
     ſche
    -1.16
     ſtate
    -1.16
     ſeveral
    -1.16
    POSITIVE LOGITS
     able
    0.66
     seen
    0.62
     held
    0.58
     taken
    0.57
     be
    0.57
    莞
    0.57
    eps
    0.57
     Be
    0.56
    Be
    0.55
    taine
    0.54
    Activations Density 0.858%

    No Known Activations