© 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. 23713
    Prev
    Next
    INDEX
    Explanations

    formal components and sections of academic research papers

    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
     surla
    -0.94
    ftagPool
    -0.80
     linkovi
    -0.78
     Wikimedijinoj
    -0.75
    CodeAttribute
    -0.71
    istoitu
    -0.70
    Boas
    -0.67
    homonymie
    -0.67
     nahilalakip
    -0.65
     estimés
    -0.63
    POSITIVE LOGITS
     BoxFit
    0.53
     szól
    0.52
    gonic
    0.49
    Démographie
    0.47
     tubo
    0.44
     követ
    0.43
     gedaan
    0.43
     retir
    0.43
    hangi
    0.42
     имен
    0.42
    Activations Density 0.018%

    No Known Activations