© 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. 12-RES-MATRYOSHKA-DC
    7. 4801
    Prev
    Next
    INDEX
    Explanations

    statements and phrases related to declarations or formal announcements

    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
    didSet
    -0.84
    oneofs
    -0.67
    耿
    -0.67
     Ox
    -0.66
    لينكات
    -0.66
    sue
    -0.66
    äksi
    -0.66
    strona
    -0.66
    endipity
    -0.65
    imanapun
    -0.65
    POSITIVE LOGITS
     declarations
    1.51
     Declare
    1.50
     declaration
    1.48
     declares
    1.40
     declare
    1.38
     declaring
    1.38
     Declaration
    1.34
     Declarations
    1.34
    Declar
    1.32
     declared
    1.30
    Activations Density 0.073%

    No Known Activations