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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11007
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving the concepts of generation and closure within algebraic structures

    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
    ValueStyle
    -0.79
     وتسجيلات
    -0.79
     Италијани
    -0.77
    ьаж
    -0.77
    tvguidetime
    -0.75
     дописавши
    -0.75
    ])));
    -0.73
     Italijani
    -0.71
     MenuView
    -0.71
    InjectAttribute
    -0.70
    POSITIVE LOGITS
     campagna
    0.46
    mena
    0.45
     Jackman
    0.44
     jScrollPane
    0.44
     breathes
    0.43
     chapa
    0.43
    randomUUID
    0.42
    usepackage
    0.41
    циал
    0.40
    ImageField
    0.40
    Activations Density 0.013%

    No Known Activations