© 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. 18-RES-MATRYOSHKA-DC
    7. 269
    Prev
    Next
    INDEX
    Explanations

    the word "one" or "one" followed by "way"

    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.18.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.18.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
     raiſ
    -0.74
    CrossRef
    -0.73
     purpoſe
    -0.73
     Jefus
    -0.73
     ―――――
    -0.72
     Meksiku
    -0.71
     occaf
    -0.68
     Majefty
    -0.68
     uſe
    -0.68
     ſch
    -0.66
    POSITIVE LOGITS
     hundred
    0.86
     thing
    0.78
     One
    0.73
    iric
    0.72
     ONE
    0.69
     another
    0.69
    One
    0.68
     jedin
    0.64
     of
    0.63
     thousand
    0.63
    Activations Density 0.738%

    No Known Activations