© 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. 2709
    Prev
    Next
    INDEX
    Explanations

    instances of the word "carry" and its variations, indicating actions related to carrying out tasks or responsibilities

    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
     Dumont
    -0.78
     Dud
    -0.77
    okovic
    -0.75
     Mathis
    -0.75
     îna
    -0.74
    fromnode
    -0.73
     inst
    -0.72
     olvides
    -0.72
    Dud
    -0.71
    enoord
    -0.69
    POSITIVE LOGITS
     Carry
    1.67
    carry
    1.61
     carry
    1.60
     carries
    1.59
     carried
    1.57
     CARRY
    1.56
     Carried
    1.51
    Carry
    1.48
    carried
    1.40
     Carriers
    1.35
    Activations Density 0.085%

    No Known Activations