© 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. 25658
    Prev
    Next
    INDEX
    Explanations

    the term "impact" in various contexts

    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
     @"/
    -0.84
    parsedMessage
    -0.83
     indisponible
    -0.83
     Gine
    -0.82
    buttonBar
    -0.81
    RRect
    -0.77
    ReusableCell
    -0.75
     GenerationType
    -0.75
    出版年
    -0.75
     وتسجيلات
    -0.75
    POSITIVE LOGITS
    Impacts
    1.02
     Impacts
    0.98
     impacts
    0.98
     Impact
    0.97
     impact
    0.94
     IMPACT
    0.91
    IMPACT
    0.87
     impacted
    0.86
    impact
    0.84
    Impact
    0.84
    Activations Density 0.012%

    No Known Activations