© 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. 23786
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "give up"

    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
    المكان
    -0.72
    mobileqq
    -0.71
     ویکی‌پدی
    -0.69
     Соб
    -0.62
    ukone
    -0.62
    ectoria
    -0.59
     opar
    -0.59
     المعيارى
    -0.58
    SourceChecksum
    -0.57
    schedulers
    -0.57
    POSITIVE LOGITS
     useParams
    0.87
     Surrender
    0.84
     surrender
    0.75
     relinquished
    0.74
     relinquish
    0.69
     surrendering
    0.68
     surrendered
    0.67
     abandonné
    0.65
     Gans
    0.65
    dymyr
    0.63
    Activations Density 0.013%

    No Known Activations