© 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. 96
    Prev
    Next
    INDEX
    Explanations

    the word "this" and related words in order to relate the current sentence to the surrounding topic

    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
     betweenstory
    -0.87
     CreateTagHelper
    -0.84
     referenties
    -0.77
     démocratie
    -0.71
     ModelExpression
    -0.64
     pareti
    -0.64
     saites
    -0.63
    aarrggbb
    -0.61
     Chwiliwch
    -0.61
     gradova
    -0.58
    POSITIVE LOGITS
     particular
    1.61
     kind
    1.41
     situation
    1.30
     type
    1.28
    particular
    1.23
     scenario
    1.17
     issue
    1.16
     thing
    1.15
     idea
    1.14
     aspect
    1.14
    Activations Density 3.449%

    No Known Activations