© 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. 10609
    Prev
    Next
    INDEX
    Explanations

    terms that indicate representation or symbolism

    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
    躇
    -0.51
    ================
    -0.50
     houſe
    -0.50
    ruch
    -0.47
    oray
    -0.47
    dropna
    -0.46
    crapers
    -0.45
    ുകൾ
    -0.45
     conne
    -0.44
    cchi
    -0.44
    POSITIVE LOGITS
    Datuak
    1.19
     الحره
    0.96
     autorytatywna
    0.95
    Населення
    0.90
    LookAnd
    0.88
    webElementXpaths
    0.83
     "..\..\..\
    0.79
     nahilalakip
    0.77
    Personendaten
    0.77
    RegressionTest
    0.76
    Activations Density 0.000%

    No Known Activations