© 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. 25879
    Prev
    Next
    INDEX
    Explanations

    numerical values that denote legal reference numbers or case identifiers

    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
     sockaddr
    -0.59
     فريبيس
    -0.59
    itinéraire
    -0.57
    dymyr
    -0.51
    setVerticalGroup
    -0.50
    RegistryLite
    -0.50
    TemporalType
    -0.49
    MigrationBuilder
    -0.49
     رح
    -0.42
    WithFormat
    -0.41
    POSITIVE LOGITS
     myſelf
    0.90
     Efq
    0.84
     Monfieur
    0.76
     uſe
    0.74
     houſe
    0.71
    näm
    0.71
     himſelf
    0.70
     themſelves
    0.69
     ſeveral
    0.68
     Majefty
    0.68
    Activations Density 0.009%

    No Known Activations