© 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. 25390
    Prev
    Next
    INDEX
    Explanations

    references to data and user-related attributes in a programming or database context

    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
    afficheront
    -0.75
     autorytatywna
    -0.73
     Signalez
    -0.72
     étoit
    -0.69
    fastjson
    -0.69
     Италијани
    -0.67
     étoient
    -0.66
     nationaux
    -0.64
     termica
    -0.64
     résine
    -0.63
    POSITIVE LOGITS
     فريبيس
    0.66
    grano
    0.54
    DebuggerNonUser
    0.51
    createFrom
    0.49
     imp
    0.48
     Te
    0.47
    дель
    0.47
    FieldBuilder
    0.45
     الرياضيه
    0.45
    ftagPool
    0.42
    Activations Density 0.069%

    No Known Activations