© 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. 22-RES-MATRYOSHKA-DC
    7. 2904
    Prev
    Next
    INDEX
    Explanations

    the word "such"

    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
    æl
    -0.50
    tanleria
    -0.48
     schemes
    -0.47
     investigations
    -0.47
    ()].
    -0.46
     antics
    -0.45
     choices
    -0.45
     results
    -0.44
    叶凌天
    -0.44
    szön
    -0.44
    POSITIVE LOGITS
    MessageTagHelper
    0.89
    IntoConstraints
    0.83
     AssemblyCulture
    0.82
    WebVitals
    0.76
    Демографія
    0.69
    DockStyle
    0.63
    tagHelperRunner
    0.63
    featureID
    0.62
    vermectin
    0.62
    ChildScrollView
    0.60
    Activations Density 0.020%

    No Known Activations