© 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. 6118
    Prev
    Next
    INDEX
    Explanations

    expressions of apology and personal communication in a conversational context

    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
    <eos>
    -0.57
    pr
    -0.52
     اح
    -0.48
    …
    -0.46
    ↵↵
    -0.43
    par
    -0.42
    ?
    -0.42
    pri
    -0.42
    iral
    -0.41
    verifyException
    -0.41
    POSITIVE LOGITS
     Efq
    1.35
     myſelf
    1.30
     Monfieur
    1.13
     pleaſure
    1.12
     Anſ
    1.11
     becauſe
    1.09
     ſeveral
    1.08
     Houſe
    1.06
     purpoſe
    1.05
     themſelves
    1.05
    Activations Density 0.451%

    No Known Activations