© 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. 9291
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "little."

    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
     referenties
    -0.65
     wings
    -0.63
     <>",
    -0.62
     للمعارف
    -0.60
    MathML
    -0.56
    enderror
    -0.56
     المعيارى
    -0.55
     tremb
    -0.55
    setKey
    -0.54
    stdc
    -0.53
    POSITIVE LOGITS
    jica
    0.69
    HasForeignKey
    0.66
    ölker
    0.64
     Dakar
    0.64
     Mim
    0.63
     useParams
    0.63
    Literat
    0.63
    ใด
    0.60
     Guidelines
    0.60
     Cili
    0.59
    Activations Density 0.016%

    No Known Activations