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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11496
    Prev
    Next
    INDEX
    Explanations

    specific city or team names in a sports context

    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
     Audiodateien
    -0.53
    رافیک
    -0.40
     University
    -0.39
     honorary
    -0.39
     aren
    -0.39
     varsity
    -0.39
     cade
    -0.38
     expelled
    -0.38
     Tyrone
    -0.38
     tam
    -0.38
    POSITIVE LOGITS
    دانشنامهٔ
    0.98
     AssemblyCompany
    0.92
    bootstrapcdn
    0.88
    <?
    0.86
    IContainer
    0.85
     Roskov
    0.85
    DockStyle
    0.83
    tagHelperRunner
    0.83
     BorderRadius
    0.82
    InputBorder
    0.82
    Activations Density 0.015%

    No Known Activations