© 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. 1363
    Prev
    Next
    INDEX
    Explanations

    words related to surveys, questionnaires, registries, and data collection

    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
     transfieras
    -0.80
    izr
    -0.70
     AssemblyProduct
    -0.63
    ThemeOverlay
    -0.60
     GetEnumerator
    -0.60
     distanciation
    -0.56
     OFDb
    -0.56
    SequentialGroup
    -0.54
     стаття
    -0.53
     appelez
    -0.53
    POSITIVE LOGITS
     records
    1.40
     record
    1.39
     Record
    1.15
     Records
    1.13
     recording
    1.13
    record
    1.13
    records
    1.12
     database
    1.08
     RECORD
    1.06
     completeness
    1.06
    Activations Density 1.771%

    No Known Activations