© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1873
    Prev
    Next
    INDEX
    Explanations

    auxiliary verb, pronoun, "there" and conjunctions.

    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
     disambiguazione
    -0.74
     kaarangay
    -0.73
     propOrder
    -0.66
    +#+
    -0.65
    تقاوى
    -0.64
     Wiktionnaire
    -0.64
    migrationBuilder
    -0.62
    #
    -0.61
    bootstrapcdn
    -0.61
    Personendaten
    -0.60
    POSITIVE LOGITS
     has
    2.23
     have
    2.06
     telah
    1.91
    has
    1.72
     đã
    1.70
    Has
    1.68
     Have
    1.59
    Have
    1.55
     Has
    1.54
    have
    1.52
    Activations Density 2.068%

    No Known Activations