© 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. 24883
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations related to set separation and dimensions

    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
    IConfiguration
    -0.61
     Normdatei
    -0.58
    hasMoreElements
    -0.55
    WebMethod
    -0.55
     дописавши
    -0.54
    koning
    -0.51
    CascadeType
    -0.51
    uzz
    -0.50
    zzleHttp
    -0.50
    CardHeader
    -0.50
    POSITIVE LOGITS
    thâu
    0.66
    RetentionPolicy
    0.63
     الحره
    0.58
    setVerticalGroup
    0.55
     ModelExpression
    0.55
    seamnă
    0.54
    WebElementEntity
    0.53
     Waray
    0.52
    ブレム
    0.52
    handedly
    0.52
    Activations Density 0.278%

    No Known Activations