© 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. 265
    Prev
    Next
    INDEX
    Explanations

    terminology related to projects, research and problem solving

    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
     signatures
    -0.91
     scenes
    -0.90
     ones
    -0.89
     slogans
    -0.88
     statuses
    -0.87
     exceptions
    -0.86
     invariants
    -0.86
     cues
    -0.86
     clichés
    -0.86
     versions
    -0.85
    POSITIVE LOGITS
     âmes
    0.83
     vœux
    0.82
     épaules
    0.82
     bénéfices
    0.78
     lèvres
    0.77
     consommateurs
    0.75
     pouvoirs
    0.75
     genoux
    0.75
     vérit
    0.71
     dieux
    0.70
    Activations Density 4.983%

    No Known Activations