© 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. 17143
    Prev
    Next
    INDEX
    Explanations

    assertions made in unit tests

    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
    ViewImports
    -0.85
    Становништво
    -0.77
    eachtet
    -0.76
    URLException
    -0.75
    CGRectMake
    -0.73
     تانيه
    -0.71
    arschijnlijk
    -0.68
    bcryptjs
    -0.66
     */,
    -0.65
    いざ
    -0.65
    POSITIVE LOGITS
    have
    0.54
     be
    0.51
    酷
    0.48
    be
    0.46
     have
    0.45
     dequeue
    0.45
     ModelExpression
    0.44
    hod
    0.43
     Grunde
    0.43
    makta
    0.42
    Activations Density 0.010%

    No Known Activations