© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 12328
    Prev
    Next
    INDEX
    Explanations

    references to legal courts

    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
    clearTimeout
    -0.54
     помочь
    -0.50
     petto
    -0.49
     ayudado
    -0.47
     assistance
    -0.47
     hjemme
    -0.46
     Assistance
    -0.46
     syke
    -0.46
     rígido
    -0.45
     increased
    -0.45
    POSITIVE LOGITS
     Roskov
    1.11
    NameInMap
    1.00
     kaarangay
    0.90
    verwijspagina
    0.87
     propOrder
    0.81
     AssemblyTitle
    0.80
    nologue
    0.80
    TestingModule
    0.72
    erapeu
    0.71
    TypedDataSet
    0.71
    Activations Density 0.002%

    No Known Activations