© 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. 2638
    Prev
    Next
    INDEX
    Explanations

    instances of the word "When" followed by actions or events

    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
    ScopeManager
    -0.73
    MemoryWarning
    -0.73
    PreAuthorize
    -0.72
    AfterClass
    -0.70
    帖最后由
    -0.69
     transférez
    -0.69
    DockStyle
    -0.68
    tangentMode
    -0.66
    Portail
    -0.65
    SourceChecksum
    -0.65
    POSITIVE LOGITS
    when
    1.40
     when
    1.38
    When
    1.27
     When
    1.20
     WHEN
    1.17
    cuando
    1.12
     cuando
    1.08
     quando
    1.06
    WHEN
    1.04
     när
    1.02
    Activations Density 0.283%

    No Known Activations