© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19466
    Prev
    Next
    INDEX
    Explanations

    terms related to expulsion and termination, particularly in political or employment 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
    CloseOperation
    -0.72
    WaitGroup
    -0.64
    Lindo
    -0.54
    itul
    -0.52
    GeneratedValue
    -0.51
     closed
    -0.50
    Devo
    -0.49
    DeleteBehavior
    -0.48
     close
    -0.48
    WithMany
    -0.48
    POSITIVE LOGITS
     expuls
    0.90
     expelled
    0.72
     expel
    0.71
     expulsion
    0.70
     Fired
    0.70
    ContentAsync
    0.70
    ())),
    0.67
    })));
    0.66
    ())));
    0.63
     evicted
    0.61
    Activations Density 0.069%

    No Known Activations