© 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. 17134
    Prev
    Next
    INDEX
    Explanations

    punctuations and numerical values associated with financial or statistical 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
     Efq
    -0.83
     juſt
    -0.78
     themſelves
    -0.77
     disponibilités
    -0.77
     ExecuteAsync
    -0.77
    RepeatedField
    -0.75
     myſelf
    -0.75
     ainfi
    -0.74
     useNavigate
    -0.74
     lenker
    -0.73
    POSITIVE LOGITS
    retin
    0.43
    laj
    0.40
    zarchiwizowane
    0.39
    __(/*!
    0.38
    </em>
    0.36
     henvisninger
    0.35
    __':
    0.35
    </strong>
    0.35
    じゃ
    0.34
     Ley
    0.33
    Activations Density 0.000%

    No Known Activations