© 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. 12-RES-MATRYOSHKA-DC
    7. 6371
    Prev
    Next
    INDEX
    Explanations

    instances of the word "through" used in various 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
    Not in Any Lists

    No Comments

    Negative Logits
     AdapterView
    -0.77
    mybatisplus
    -0.76
     blessés
    -0.74
     Below
    -0.73
     Aza
    -0.73
     Púb
    -0.72
     récomp
    -0.72
     متعلقه
    -0.72
     prisonniers
    -0.72
    ContentAlignment
    -0.71
    POSITIVE LOGITS
    through
    1.70
    Through
    1.67
     through
    1.58
     Through
    1.57
    THROUGH
    1.56
     THROUGH
    1.44
     thru
    1.27
    thru
    1.22
     Thru
    1.16
     durch
    1.13
    Activations Density 0.188%

    No Known Activations