© 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. 32539
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly related to statistical or experimental data and their variations

    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
     invokingState
    -0.60
     مواليد
    -0.54
    iement
    -0.50
     onCancelled
    -0.48
    !("{
    -0.47
    ίκ
    -0.46
    ặp
    -0.46
    mereka
    -0.45
     Rhine
    -0.45
     ModelExpression
    -0.45
    POSITIVE LOGITS
    findpost
    0.69
    tagext
    0.68
    CodedInputStream
    0.67
    MigrationBuilder
    0.65
     iprot
    0.63
    DockStyle
    0.60
     oprot
    0.56
    urlpatterns
    0.56
    Personendaten
    0.56
     kasarigan
    0.55
    Activations Density 0.581%

    No Known Activations