© 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. 12-RES-MATRYOSHKA-DC
    7. 25238
    Prev
    Next
    INDEX
    Explanations

    instances of the word "join" and its variations in different contexts

    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
    Negative Logits
     Rauch
    -0.73
    Према
    -0.65
    WebElementEntity
    -0.63
    usitis
    -0.63
     Flur
    -0.60
    IBUS
    -0.60
     resourceCulture
    -0.59
     kỳ
    -0.59
    Alsace
    -0.59
     Kuru
    -0.58
    POSITIVE LOGITS
     JOIN
    1.52
     joining
    1.48
     join
    1.43
     joins
    1.41
    JOIN
    1.41
     Joining
    1.41
    join
    1.38
     Joins
    1.36
     rejoin
    1.30
    Joining
    1.27
    Activations Density 0.033%

    No Known Activations