© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-RES-MATRYOSHKA-DC
    7. 478
    Prev
    Next
    INDEX
    Explanations

    words with the suffixes "ity", "ive", "tic", "able", "ical", "al" and "ous"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.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
     ſta
    -0.79
     تضيفلها
    -0.79
     purpoſe
    -0.72
     ſmall
    -0.67
     Basta
    -0.66
     houſe
    -0.66
    TypedDataSet
    -0.66
     leaſt
    -0.65
     pleaſure
    -0.65
     ſtand
    -0.64
    POSITIVE LOGITS
    entibus
    0.61
     ammat
    0.50
    mentes
    0.48
     atividade
    0.48
     võimal
    0.47
    geſ
    0.47
     cible
    0.46
     aluguel
    0.46
    -\\
    0.45
     mentes
    0.45
    Activations Density 1.904%

    No Known Activations