© 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. 11638
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to mappings and projections in algebraic structures

    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
    MLLoader
    -0.85
    Personensuche
    -0.77
     &___
    -0.76
    ibatis
    -0.70
    MessageOf
    -0.69
    elemField
    -0.69
    :✨
    -0.66
     GenerationType
    -0.66
    LabelTagHelper
    -0.66
    <?
    -0.65
    POSITIVE LOGITS
    later
    0.44
     Central
    0.44
     Eier
    0.43
     Wandel
    0.43
     huevo
    0.42
    Clazz
    0.42
     izquier
    0.42
    schul
    0.42
    hibitions
    0.41
    all
    0.41
    Activations Density 0.013%

    No Known Activations