© 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. 18-RES-MATRYOSHKA-DC
    7. 1409
    Prev
    Next
    INDEX
    Explanations

    words related to study results, data and official facilities

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     and
    -1.09
     or
    -0.87
     &
    -0.84
     nahilalakip
    -0.75
     respectively
    -0.68
     respectivement
    -0.65
     gyhoeddwyd
    -0.64
     masing
    -0.64
    and
    -0.63
    respectively
    -0.62
    POSITIVE LOGITS
    migrationBuilder
    0.64
    følgelig
    0.62
    aine
    0.61
    HLT
    0.60
    icamente
    0.57
    endphp
    0.57
    sweise
    0.57
    bleau
    0.57
     alike
    0.56
    stuffs
    0.56
    Activations Density 2.325%

    No Known Activations