© 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. 136
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs, conjunctions, and related surrounding words

    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
     nakalista
    -0.60
     endwhile
    -0.54
    VIAF
    -0.54
    他会
    -0.52
     Familienname
    -0.52
    addGap
    -0.51
    rungsseite
    -0.51
    ברס
    -0.51
    κτηρισ
    -0.51
    pyplot
    -0.49
    POSITIVE LOGITS
     not
    2.17
     não
    1.86
     tidak
    1.78
     neither
    1.70
     nicht
    1.70
     never
    1.68
     không
    1.66
     ikke
    1.66
     doesn
    1.59
     niet
    1.58
    Activations Density 6.202%

    No Known Activations