© 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
    2. Gemma-2-2B
    3. 24-RES-MATRYOSHKA-DC
    4. 859
    Prev
    Next
    INDEX
    Explanations

    the word "and," sometimes in combination with other coordinating conjunctions or words related to social and societal matters

    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.24.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.24.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
    tagHelperRunner
    -1.01
    RTEE
    -0.75
     незавершена
    -0.71
    OGND
    -0.71
     rectangles
    -0.68
    出版年
    -0.64
     circles
    -0.63
     समीक्षाओं
    -0.61
     triangles
    -0.60
    MENAFN
    -0.60
    POSITIVE LOGITS
    rogens
    0.65
     illetve
    0.63
    /
    0.59
     sometimes
    0.59
     ibland
    0.59
     non
    0.55
    deals
    0.54
     ggf
    0.51
    sometimes
    0.51
     manchmal
    0.50
    Activations Density 0.807%

    No Known Activations