© 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. 388
    Prev
    Next
    INDEX
    Explanations

    words related to language structure and vocabulary

    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
    IntoConstraints
    -0.59
    ISupport
    -0.59
    ględ
    -0.57
    OrNil
    -0.56
     propOrder
    -0.56
     Geraadpleegd
    -0.53
    DockStyle
    -0.51
    IVEREF
    -0.50
    RenderAtEndOf
    -0.49
     createState
    -0.49
    POSITIVE LOGITS
     words
    1.32
     word
    1.30
     language
    1.19
     English
    1.16
     pronunciation
    1.16
     linguistic
    1.09
     vocabulary
    1.09
     phonetic
    1.06
     phrase
    1.05
     spoken
    1.05
    Activations Density 2.980%

    No Known Activations