© 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. 18666
    Prev
    Next
    INDEX
    Explanations

    phrases related to liability and legal conditions

    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
    最快更新
    -0.56
    makeConstraints
    -0.54
     préférence
    -0.54
    googleapis
    -0.53
    creds
    -0.53
    createCanvas
    -0.53
    ->___
    -0.52
     GenerationType
    -0.51
    lepší
    -0.51
     perhaps
    -0.50
    POSITIVE LOGITS
    \{\\
    0.65
    OGND
    0.63
    :✨
    0.60
    NamedQueries
    0.59
    ernalia
    0.56
    cionario
    0.51
    Deep
    0.50
     '\\;'
    0.50
    出版年
    0.50
    EqualsAnd
    0.49
    Activations Density 0.002%

    No Known Activations