© 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. 12-RES-MATRYOSHKA-DC
    7. 1593
    Prev
    Next
    INDEX
    Explanations

    the word "although" and its variants

    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
     future
    -0.62
    NavItem
    -0.60
     AssemblyCulture
    -0.59
     maka
    -0.56
    žiu
    -0.54
     So
    -0.54
    どこ
    -0.52
     selanjutnya
    -0.52
    mozilla
    -0.52
    newData
    -0.51
    POSITIVE LOGITS
    ostante
    1.15
     THOUGH
    1.12
    though
    1.11
    withstanding
    1.07
    Meski
    1.06
    Though
    1.05
    ांकि
    1.05
     though
    1.05
    although
    1.04
     itſelf
    1.03
    Activations Density 0.265%

    No Known Activations