© 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. 31852
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical averages

    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
     snippetHide
    -0.75
    FormTagHelper
    -0.67
    oredCriteria
    -0.67
    তথ্যসূত্র
    -0.65
    تقاوى
    -0.64
    #+#
    -0.63
     contiennent
    -0.61
     дописавши
    -0.60
     getItemCount
    -0.59
    ]]=
    -0.59
    POSITIVE LOGITS
     fus
    0.54
    вест
    0.49
    nių
    0.48
    lus
    0.45
     pinulongan
    0.45
    bereits
    0.45
    ToMany
    0.45
    न्
    0.44
    ARIUS
    0.44
     VIDEOTAPE
    0.44
    Activations Density 0.003%

    No Known Activations