© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11220
    Prev
    Next
    INDEX
    Explanations

    instances of the word "until" or "till."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    Hrsg
    -0.60
     (
    -0.52
     ‘
    -0.50
     li
    -0.50
     dor
    -0.49
    ,
    -0.49
    }}^
    -0.49
    :
    -0.48
    ंप
    -0.48
    ’
    -0.46
    POSITIVE LOGITS
     nahilalakip
    1.13
     itſelf
    1.09
     myſelf
    1.08
     raiſ
    1.05
     beginnetje
    1.02
    ContentAsync
    1.00
     Monfieur
    1.00
     poffible
    0.99
     themſelves
    0.98
     ―――――
    0.97
    Activations Density 0.008%

    No Known Activations