© 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. 24-RES-MATRYOSHKA-DC
    7. 683
    Prev
    Next
    INDEX
    Explanations

    the word "was"

    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
    now
    -0.72
     now
    -0.70
    Now
    -0.69
     Sekarang
    -0.68
    Currently
    -0.67
     maintenant
    -0.63
     désormais
    -0.63
     currently
    -0.63
    現在
    -0.62
    现在
    -0.61
    POSITIVE LOGITS
     originally
    1.34
     ursprünglich
    1.13
     originalmente
    1.09
    originally
    1.07
     previously
    1.06
     autrefois
    1.05
     initially
    0.98
    Originally
    0.97
     Originally
    0.97
     recently
    0.96
    Activations Density 0.698%

    No Known Activations