© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 15778
    Prev
    Next
    INDEX
    Explanations

    expressions indicating clarity or certainty in arguments

    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
    Negative Logits
     ses
    -0.51
    ط
    -0.51
     MotionEvent
    -0.47
    Revenir
    -0.47
     يتيمه
    -0.47
    con
    -0.45
    <eos>
    -0.45
    Con
    -0.45
    жели
    -0.45
     t
    -0.44
    POSITIVE LOGITS
     itſelf
    1.09
     myſelf
    1.01
     Efq
    0.87
     Jefus
    0.85
     purpoſe
    0.82
     themſelves
    0.81
    ſelf
    0.77
     raiſ
    0.76
     leſs
    0.76
     reaſon
    0.73
    Activations Density 0.054%

    No Known Activations