© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 28371
    Prev
    Next
    INDEX
    Explanations

    codes or references in scientific documents

    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
      (
    -0.65
    PMailer
    -0.54
    Numerade
    -0.53
    bourhood
    -0.48
    Eksterne
    -0.46
    èl
    -0.46
    sohn
    -0.45
    isalpha
    -0.44
     el
    -0.44
    ịnh
    -0.44
    POSITIVE LOGITS
    ThroughAttribute
    0.74
     transfieras
    0.73
    цездатний
    0.73
     nahilalakip
    0.71
    expandindo
    0.71
    RegressionTest
    0.70
     indisponible
    0.70
    PreferredItem
    0.68
     femei
    0.66
     ProtoMessage
    0.66
    Activations Density 0.015%

    No Known Activations