© 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. 20417
    Prev
    Next
    INDEX
    Explanations

    the word "but" and its variations to signal contrast or contradiction

    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
    Personensuche
    -0.84
     amphi
    -0.74
     Saxons
    -0.73
    Cyfeiriadau
    -0.71
     تضيفلها
    -0.70
     gynhyrchwyd
    -0.70
     noDo
    -0.68
    vece
    -0.68
    nocześnie
    -0.68
     encima
    -0.68
    POSITIVE LOGITS
    qxd
    0.55
    eqn
    0.52
     μ
    0.52
     UnityEngine
    0.52
    hets
    0.50
    Seine
    0.50
    paramref
    0.50
    %
    0.50
    Koordinaten
    0.50
    }")]
    0.49
    Activations Density 0.025%

    No Known Activations