© 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. 30073
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal privacy and sensitive information

    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
    Not in Any Lists

    No Comments

    Negative Logits
     referenties
    -0.65
    Filmografie
    -0.54
     crossorigin
    -0.50
    rrggbb
    -0.47
    kosť
    -0.45
    ӳ
    -0.44
    TemporalType
    -0.43
    ẵng
    -0.42
    Портал
    -0.42
     théorie
    -0.42
    POSITIVE LOGITS
    EndInit
    0.77
    tagHelper
    0.65
    horesis
    0.62
    BeginContext
    0.62
    GetKeyDown
    0.61
    WriteLine
    0.60
     Exacts
    0.56
    posób
    0.56
     blur
    0.55
    MoveNext
    0.55
    Activations Density 0.239%

    No Known Activations