© 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. 29653
    Prev
    Next
    INDEX
    Explanations

    blocks of whitespace or indentation in code

    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
     eventdata
    -0.73
    inį
    -0.58
    первых
    -0.57
     resourceCulture
    -0.55
    andExpect
    -0.53
     pagal
    -0.53
    nextLine
    -0.51
     Foer
    -0.51
    rimo
    -0.50
     couple
    -0.49
    POSITIVE LOGITS
    amaño
    0.63
    Drupal
    0.59
    Hochspringen
    0.57
    ={`/
    0.54
    TypedDataSet
    0.53
    DebuggerNonUser
    0.52
     Prus
    0.52
     órdenes
    0.52
     Familienname
    0.52
     keras
    0.52
    Activations Density 0.006%

    No Known Activations