© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 1334
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "understand/understood"

    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
    CrossRef
    -0.62
    tagHelper
    -0.61
    datagrid
    -0.56
     resultCode
    -0.54
    orianCalendar
    -0.52
    glBindTexture
    -0.51
    toggler
    -0.50
    ttino
    -0.50
    orsese
    -0.50
    jupiter
    -0.50
    POSITIVE LOGITS
    understand
    1.20
     Understand
    1.13
     why
    1.11
    understood
    1.09
    Understand
    1.09
     understands
    1.08
     understand
    1.02
     understood
    0.98
     understandable
    0.95
     begrij
    0.91
    Activations Density 0.149%

    No Known Activations