© 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. 18-RES-MATRYOSHKA-DC
    7. 782
    Prev
    Next
    INDEX
    Explanations

    the word "when" followed by other words

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
     propOrder
    -0.83
    帖最后由
    -0.78
     وتسجيلات
    -0.65
    NameInMap
    -0.65
    djangoproject
    -0.60
    WriteAttribute
    -0.59
     attirer
    -0.59
     estekak
    -0.58
     Réponses
    -0.56
    queryInterface
    -0.56
    POSITIVE LOGITS
     when
    0.94
    when
    0.93
     compared
    0.93
    When
    0.87
     WHEN
    0.86
    WHEN
    0.81
     When
    0.81
     considering
    0.78
    Cuando
    0.77
     Cuando
    0.75
    Activations Density 0.508%

    No Known Activations