© 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. 2-RES-MATRYOSHKA-DC
    7. 6842
    Prev
    Next
    INDEX
    Explanations

    references to arrests or the act of being taken into custody

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     catch
    -0.76
    catch
    -0.64
     catches
    -0.59
     Catch
    -0.56
     fitted
    -0.56
     adaptado
    -0.54
    Catch
    -0.53
    awtextra
    -0.53
     CATCH
    -0.53
    fitted
    -0.52
    POSITIVE LOGITS
     arrest
    2.80
     Arrest
    2.47
     arrests
    2.36
    arrest
    2.36
     arrested
    2.30
    Arrest
    2.05
     arresting
    1.77
     Arrested
    1.65
    逮捕
    1.16
     arre
    0.99
    Activations Density 0.007%

    No Known Activations