© 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. 303
    Prev
    Next
    INDEX
    Explanations

    numbers and some words relating to data processing or statistics

    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
     épaules
    -1.45
     vœux
    -1.37
     lèvres
    -1.36
     bienfaits
    -1.31
     négociations
    -1.30
     bénéfices
    -1.26
     âmes
    -1.25
     pouvoirs
    -1.20
     oreilles
    -1.20
     genoux
    -1.16
    POSITIVE LOGITS
     items
    0.90
     sets
    0.89
     pieces
    0.89
     formats
    0.89
     instances
    0.88
     versions
    0.86
     structures
    0.85
     cases
    0.85
     situations
    0.82
     groups
    0.81
    Activations Density 9.509%

    No Known Activations