© 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. 11689
    Prev
    Next
    INDEX
    Explanations

    references and citations in academic writing

    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
    AddTagHelper
    -0.75
    JspWriter
    -0.70
     propOrder
    -0.69
    ashian
    -0.68
    WillAppear
    -0.67
    brainly
    -0.66
    IZABETH
    -0.65
     
    -0.63
    ]--;
    -0.61
    sbericht
    -0.60
    POSITIVE LOGITS
     including
    0.54
    including
    0.52
     successively
    0.49
     includ
    0.44
    陆续
    0.44
    ễm
    0.42
     noqa
    0.42
     Including
    0.42
    Including
    0.41
     stack
    0.41
    Activations Density 0.082%

    No Known Activations