© 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. 20710
    Prev
    Next
    INDEX
    Explanations

    statements regarding claims and testimonies

    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
    orsese
    -0.63
    
    -0.59
    ніципа
    -0.57
    UnusedPrivate
    -0.57
    ⇑
    -0.56
     otomatig
    -0.56
    onViewCreated
    -0.55
    脚注の使い方
    -0.54
     Paglinawan
    -0.53
    COUVER
    -0.52
    POSITIVE LOGITS
    TagHelper
    0.52
    trup
    0.50
    engertian
    0.49
     ""){
    0.47
     '
    0.47
     Mâ
    0.47
    '){
    0.47
    TagHelpers
    0.46
    atamente
    0.45
    okin
    0.45
    Activations Density 0.281%

    No Known Activations