© 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. 32064
    Prev
    Next
    INDEX
    Explanations

    emphatic or transitional words and phrases that indicate a change or conclusion in thought

    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
     be
    -0.71
    toBe
    -0.62
     nearer
    -0.61
     closer
    -0.60
    
    -0.59
     confounding
    -0.59
     fá
    -0.58
     provoking
    -0.57
    fey
    -0.56
     Ques
    -0.56
    POSITIVE LOGITS
    Expedia
    0.81
     did
    0.80
     gave
    0.77
    tôi
    0.76
    Kjelder
    0.74
    manteau
    0.73
    amaño
    0.73
     préférable
    0.72
    [])
    0.71
    RegistryLite
    0.70
    Activations Density 0.121%

    No Known Activations