© 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. 12-RES-MATRYOSHKA-DC
    7. 31086
    Prev
    Next
    INDEX
    Explanations

    references to rights and preservation of identity for individuals in Denmark

    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
    exec
    -0.48
    yr
    -0.43
    one
    -0.42
    ft
    -0.39
     such
    -0.38
     ‘
    -0.38
    ắc
    -0.38
    ‘
    -0.37
    <strong>
    -0.36
     K
    -0.36
    POSITIVE LOGITS
    rungsseite
    1.37
    ftagPool
    1.35
    AddTagHelper
    1.30
     initComponents
    1.29
     estekak
    1.23
    ReusableCell
    1.22
     autorytatywna
    1.21
    Geplaatst
    1.20
    abestanden
    1.16
     CreateTagHelper
    1.14
    Activations Density 0.002%

    No Known Activations