© 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. 24-RES-MATRYOSHKA-DC
    7. 1090
    Prev
    Next
    INDEX
    Explanations

    acronyms associated with legal or medical terminology, or fragments of domain names.

    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.24.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.24.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
     ASR
    -0.39
     CCM
    -0.38
     Ruskin
    -0.38
     Ruh
    -0.37
     Bana
    -0.36
    FetchType
    -0.36
     Ashraf
    -0.36
     Hauser
    -0.35
     OCS
    -0.35
     Somerville
    -0.33
    POSITIVE LOGITS
     CSD
    0.91
     Kidd
    0.89
     SED
    0.88
     Kud
    0.86
     td
    0.84
    iad
    0.83
    tid
    0.83
     CED
    0.83
     LD
    0.82
    rdd
    0.82
    Activations Density 1.924%

    No Known Activations