© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 198
    Prev
    Next
    INDEX
    Explanations

    JSON-like data structures consisting of key-value pairs enclosed in quotes and brackets with the labels "type", "name", "description", "title", and "version".

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     nemico
    -0.63
     espagnole
    -0.56
     pericolo
    -0.53
     policiales
    -0.53
     traditionnelle
    -0.53
     newArr
    -0.53
     vicina
    -0.51
     judiciaire
    -0.49
     indústria
    -0.48
     letteratura
    -0.48
    POSITIVE LOGITS
     name
    1.20
     type
    1.13
     description
    1.07
     propOrder
    1.03
    GEBURTSDATUM
    1.02
     AssemblyTitle
    0.96
     title
    0.95
     id
    0.95
     location
    0.92
     status
    0.90
    Activations Density 3.721%

    No Known Activations