© 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. 22-RES-MATRYOSHKA-DC
    7. 2799
    Prev
    Next
    INDEX
    Explanations

    the word "travel" and related words, and gives a boost if "the" follows "travel"

    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
    herited
    -0.54
     Amm
    -0.54
    fulness
    -0.51
     géant
    -0.51
    LabelTagHelper
    -0.51
    aratus
    -0.50
    солю
    -0.50
     overlooking
    -0.50
    lessly
    -0.50
     rowspan
    -0.49
    POSITIVE LOGITS
     Travelers
    0.81
     travelers
    0.73
     TRAVEL
    0.72
    WriteBarrier
    0.72
     Travel
    0.72
    Travel
    0.71
    GroupLayout
    0.70
     travel
    0.69
     travellers
    0.69
     Destinations
    0.69
    Activations Density 0.096%

    No Known Activations