© 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. 17744
    Prev
    Next
    INDEX
    Explanations

    terms related to the process of harvesting

    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
     referenties
    -0.88
     InputDecoration
    -0.82
     препратки
    -0.75
    riwal
    -0.71
     Olivenöl
    -0.69
    bitField
    -0.66
    msford
    -0.66
    complexContent
    -0.65
     numberWith
    -0.63
    })^
    -0.61
    POSITIVE LOGITS
     harvested
    1.41
     harvest
    1.40
     harvests
    1.36
     Harvesting
    1.35
     Harvest
    1.34
    Harvest
    1.30
    harvest
    1.27
     harvesting
    1.26
     harves
    1.11
     cosecha
    1.05
    Activations Density 0.004%

    No Known Activations